Upload
dinhdat
View
212
Download
0
Embed Size (px)
Citation preview
18th International Conference on Neural Information Processing
November 13-17, 2011, Majesty Plaza, Shanghai, China
Program & Abstracts
Technical Sponsors
Asia Pacific Neural Network Assembly
Japanese Neural Network Society
Financial Sponsors
National Natural Science Foundation of China
Shanghai Hyron Software Co., LTD
Hitachi (China) Research & Development
Corporation
Fujitsu Research and Development Center,
CO., LTD
Table of Content
Welcome Message ......................................................................................................... I
ICONIP 2011 Organization ......................................................................................... III
Venue Information ....................................................................................................... IX
ICONIP2011 Technical Program at a Glance ................................................................ 1
Keynotes & Plenary Speakers ........................................................................................ 4
ICONIP2011 Technical Program ................................................................................. 14
Book of Abstracts ........................................................................................................ 33
Author Index ................................................................................................................ 88
Workshops Programs…………………...………………………………………………………99
I
Welcome Message
On behalf of the Organizing Committee, it is our pleasure to welcome you to participate in the Eighteenth International Conference on Neural Information Processing (ICONIP2011). ICONIP is the annual conference of the Asia Pacific Neural Network Assembly (APNNA). ICONIP 2011 aims to provide a high-level international forum for scientists, engineers, educators, and students to address new challenges, share solutions, and discuss future research directions in neural information processing and real-world applications.
The scientific program of the ICONIP2011 presents an outstanding spectrum of over 260 research papers from forty two countries and regions, emerging from multidisciplinary areas such as computational neuroscience,cognitive science, computer science, neural engineering, computer vision, machine learning, pattern recognition, natural language processing, and many more to focus on the challenges of developing future technologies for neural information processing. In addition to the contributed papers, we are particularly pleased by ten plenary speeches by world-renowned scholars: Shun-ichi Amari, Kunihiko Fukushima, Aike Guo, Lei Xu, Jun Wang, DeLiang Wang, Derong Liu, Xin Yao, Soo-Young Lee, and Nikola Kasabov. The program will also include six excellent tutorials by David Cai, Irwin King, Pei-Ji Liang, Hiroshi Mamitsuka, Ming Zhou, Hang Li, and Shanfeng Zhu. The conference will be followed by three post-conference Workshops held in Hangzhou, November 18, 2011: “ICONIP2011Workshop on Brain-Computer Interface and Applications”, organized by Bao-Liang Lu, Liqing Zhang, and Chin-Teng Lin; “The 4th International Workshop on Data Mining and Cybersecurity”, organized by Paul S. Pang, Tao Ban, Youki Kadobayashi, and Jungsuk Song; and “ICONIP 2011 Workshop on Recent Advances in Nature Inspired Computation and Its Applications”, organized by Xin Yao and Shan He.
ICONIP2011 organizers would like to thank all special session organizers for their effort and time for enriching the topics and program of the conference. The program will include the following thirteen special sessions: “Advances in Computational Intelligence Methods based Pattern Recognition”, organized by Kai-Zhu Huang and Jun Sun; “Biologically Inspired Vision and Recognition”, organized by Jun Miao, Libo Ma, Liming Zhang, JuyangWeng and Xilin Chen; “Bio-Medical Data Analysis”, organized by Jie Yang and Guo-Zheng Li; “Brain Signal Processing”, organized by Jian-Ting Cao, Tomasz M. Rutkowski, Toshihisa Tanaka, and Liqing Zhang; “Brain-Realistic Models for Learning, Memory and Embodied Cognition”, organized by Huajin Tang and Jun Tani; “Clifford Algebraic Neural Networks”, organized by Tohru Nitta and Yasuaki Kuroe; “Combining Multiple Learners”, organized by Younès Bennani, Nistor Grozavu, Mohamed Nadif, and Nicoleta Rogovschi; “Computational Advances in Bioinformatics”, organized by Jonathan H. Chan; “Computational-Intelligent Human Computer Interaction”, organized by Chin-Teng Lin, Jyh-Yeong Chang, John Kar-kin Zao, Yong-Sheng Chen, and Li-Wei Ko;
II
“Evolutionary Design and Optimisation”, organized by RuhulSarker and Mao-Lin Tang; “Human-Originated Data Analysis and Implementation”, organized by Hyeyoung Park and Sang-Woo Ban; “Natural Language Processing and Intelligent Web Information Processing”, organized by Xiao-Long Wang, Rui-Feng Xu, and Hai Zhao; and “Integrating Multiple Nature-inspired Approaches”, organized by Shan He and Xin Yao. The ICONIP2011 and the post-conference Workshops events would not have achieved their success without the generous contributions of many organizations and volunteers. The organizers would also like to express sincere thanks to APNNA for the sponsorship, to the Chinese Neural Networks Council, International Neural Network Society, and Japanese Neural Network Society for their technical co-sponsorship, to Shanghai Jiao Tong University for its financial and logistic supports, and to National Natural Science Foundation of China, Shanghai Hyron Software Co., LTD, Microsoft Research Asia, Hitachi (China) Research & Development Corporation, Fujitsu Research and Development Center, CO., LTD, and Eagle Canyon for their financial supports. We are very pleased to acknowledge the support of the conference Advisory Committee, the APNNA Governing Board and Past Presidents for their guidance, and the members of the International Program Committee and additional reviewers for reviewing the papers. Particularly, the organizers would like to thank the proceedings publisher, Springer, for publishing the proceedings in Lecture Notes in Computer Science. We want to give special thanks to Web managers, HaoyuCai and Dong Li, and the publication team comprising Li-Chen Shi, Yong Peng, Cong Hui, Bing Li, Dan Nie, Ren-Jie Liu, Tian-Xiang Wu, Xue-Zhe Ma, Shao-Hua Yang, Yuan-Jian Zhou and Cong Xie for checking the accepted papers in a short period of time. Last but not least, the organizers would like to thank all the authors, speakers, audience, and volunteers. We hope that you enjoy your time in Shanghai as well as the technical and social programs at ICONIP2011. Yours Sincerely,
Liqing Zhang
Bao-Liang Lu James T. Kwok
ICONIP2011 General Chair ICONIP2011 Program Co-Chairs
III
ICONIP 2011 Organization
Organizer
Shanghai Jiao Tong University
Sponsor
Asia Pacific Neural Network Assembly
Financial Co-sponsors
Shanghai Jiao Tong University
National Natural Science Foundation of China
Shanghai Hyron Software Co., LTD
Microsoft Research Asia
Hitachi (China) Research & Development Corporation
Fujitsu Research and Development Center, Co., LTD
Eagle Canyon
Technical Co-sponsors
China Neural Networks Council
International Neural Network Society
Japanese Neural Network Society
Honorary Chair
Shun-ichi Amari, Brain Science Institute, RIKEN, Japan
Advisory Committee Chairs
Shoujue Wang, Institute of Semiconductors, Chinese Academy of Sciences, China
Aike Guo, Institute of Neuroscience, Chinese Academy of Sciences, China
Liming Zhang, Fudan University, China
Advisory Committee Members
Sabri Arik, Istanbul University, Turkey
Jonathan H. Chan, King Mongkut'sUniversity of Technology, Thailand
Wlodzislaw Duch, Nicolaus Copernicus University, Poland
Tom Gedeon, Australian National University, Australia
Yuzo Hirai, University of Tsukuba, Japan
Ting-Wen Huang, Texas A&M University, Qatar
Akira Hirose, University of Tokyo, Japan
Nik Kasabov, AucklandUniversity of Technology, New Zealand
Irwin King, The Chinese University of Hong Kong, Hong Kong
Weng-Kin Lai, MIMOS, Malaysia
Min-Ho Lee, Kyungpoor National University, Korea
Soo-Young Lee, Korea Advanced Institute of Science and Technology, Korea
IV
Andrew Chi-Sing Leung, CityUniversity of Hong Kong, Hong Kong
Chin-Teng Lin, National Chiao Tung University, Taiwan
Derong Liu, University of Illinois at Chicago, USA
Noboru Ohnishi, Nagoya University, Japan
Nikhil R. Pal, Indian Statistical Institute, India
John Sum, National Chung Hsing University, Taiwan
DeLiang Wang, Ohio State University, USA
Jun Wang, The Chinese University of Hong Kong, Hong Kong
Kevin Wong, Murdoch University, Australia
Lipo Wang, Nanyang Technological University, Singapore
Xin Yao, University of Birmingham, UK
Liqing Zhang, Shanghai Jiao Tong University, China
General Chair
Bao-Liang Lu, Shanghai Jiao Tong University, China
Program Chairs
Liqing Zhang, Shanghai Jiao Tong University, China
James T.Y. Kwok, Hong KongUniversity of Science and Technology, Hong Kong
Organizing Chair
Hongtao Lu, Shanghai Jiao Tong University, China
Workshop Chairs
Guangbin Huang, Nanyang Technological University, Singapore
Jie Yang, Shanghai Jiao Tong University, China
Xiaorong Gao, Tsinghua University, China
Special Sessions Chairs
Changshui Zhang, Tsinghua University, China
Akira Hirose, University of Tokyo, Japan
Minho Lee, Kyungpoor National University, Korea
Tutorial Chair
Si Wu, Institute of Neuroscience, Chinese Academy of Sciences, China
Publications Chairs
Yuan Luo, Shanghai Jiao Tong University, China
Tianfang Yao, Shanghai Jiao Tong University, China
Yun Li, NanjingUniversity of Posts and Telecommunications, China
Publicity Chairs
Kazushi Ikeda, Nara Institute of Science and Technology, Japan
Shaoning Pang, Unitec Institute of Technology, New Zealand
V
Chi-Sing Leung, City University of Hong Kong, China
Registration Chair
Hai Zhao, Shanghai Jiao Tong University, China
Financial Chair
YangYang, Shanghai Maritime University, China
Local Arrangement Chairs
Guang Li, Zhejiang University, China
Fang Li, Shanghai Jiao Tong University, China
Secretary
Xun Liu, Shanghai Jiao Tong University, China
Program Committee
Shigeo Abe
Bruno Apolloni
Sabri Arik
Sang-Woo Ban
Jianting Cao
Jonathan Chan
Songcan Chen
Xilin Chen
Yen-Wei Chen
Yiqiang Chen
Siu-Yeung David Cho
Sung-Bae Cho
Seungjin Choi
Andrzej Cichocki
Jose Alfredo Ferreira Costa
Sergio Cruces
Ke-Lin Du
Simone Fiori
John Qiang Gan
Junbin Gao
Xiaorong Gao
Nistor Grozavu
Ping Guo
Qing-Long Han
Shan He
Akira Hirose
Jinglu Hu
Guang-Bin Huang
Kaizhu Huang
Amir Hussain
Danchi Jiang
Tianzi Jiang
Tani Jun
Joarder Kamruzzaman
Shunshoku Kanae
Okyay Kaynak
John Keane
Sungshin Kim
Li-Wei Ko
Takio Kurita
Minho Lee
Chi Sing Leung
Chunshien Li
Guo-Zheng Li
Junhua Li
Wujun Li
Yuanqing Li
Yun Li
Huicheng Lian
Peiji Liang
Chin-Teng Lin
Hsuan-Tien Lin
Hongtao Lu
Libo Ma
Malik Magdon-Ismail
Robert(Bob) McKay
VI
Duoqian Miao
Jun Miao
Vinh Nguyen
Tohru Nitta
Toshiaki Omori
Hassab Elgawi Osman
Seiichi Ozawa
Paul Pang
Hyeyoung Park
Alain Rakotomamonjy
Sarker Ruhul
Naoyuki Sato
Lichen Shi
Jochen J. Steil
John Sum
Jun Sun
Toshihisa Tanaka
Huajin Tang
Maolin Tang
Dacheng Tao
Qing Tao
Peter Tino
Ivor Tsang
Michel Verleysen
Bin Wang
Rubin Wang
Xiao-Long Wang
Yimin Wen
Young-Gul Won
Yao Xin
Rui-Feng Xu
Haixuan Yang
Jie Yang
Yang Yang
Yingjie Yang
Zhirong Yang
Dit-Yan Yeung
Jian Yu
Zhigang Zeng
Jie Zhang
Kun Zhang
Hai Zhao
Zhihua Zhou
Reviewers Pablo Aguilera
Lifeng Ai
Elliot Anshelevich
Bruno Apolloni
Sansanee Auephanwiriyakul
Hongliang Bai
Rakesh Kr Bajaj
Tao Ban
Gang Bao
Simone Bassis
Anna Belardinelli
Yoshua Bengio
Sergei Bezobrazov
Yinzhou Bi
Alberto Borghese
Tony Brabazon
Guenael Cabanes
Faicel Chamroukhi
Feng-Tse Chan
Hong Chang
Liang Chang
Aaron Chen
Caikou Chen
Huangqiong Chen
Huanhuan Chen
Kejia Chen
Lei Chen
Qingcai Chen
Yin-Ju Chen
Yuepeng Chen
Jian Cheng
Wei-Chen Cheng
Yu Cheng
Seong-Pyo Cheon
Minkook Cho
Heeyoul Choi
Yong-Sun Choi
Shihchieh Chou
Angelo Ciaramella
Sanmay Das
Satchidananda Dehuri
Ivan Duran Diaz
Tom Diethe
Ke Ding
Lijuan Duan
Chunjiang Duanmu
Sergio Escalera
Aiming Feng
Remi Flamary
Gustavo Fontoura
Zhenyong Fu
Zhouyu Fu
Xiaohua Ge
Alexander Gepperth
M.Mohamad Ghassany
Adilson Gonzaga
Alexandre Gravier
Jianfeng Gu
Lei Gu
Zhong-Lei Gu
VII
Naiyang Guan
Pedro Antonio Gutiérrez
Jing-Yu Han
Xianhua Han
Ross Hayward
Hanlin He
Akinori Hidaka
Hiroshi Higashi
Arie Hiroaki
Eckhard Hitzer
Gray Ho
Kevin Ho
Xia Hua
Mao Lin Huang
Qinghua Huang
Sheng-Jun Huang
Tan Ah Hwee
Kim Min Hyeok
Teijiro Isokawa
Wei Ji
Zheng Ji
Caiyan Jia
Nanlin Jin
Liping Jing
Yoonseop Kang
Chul Su Kim
Kyung-Joong Kim
Saehoon Kim
Yong-Deok Kim
Irwin King
Jun Kitazono
Masaki Kobayashi
Yasuaki Kuroe
Hiroaki Kurokawa
Chee Keong Kwoh
James Kwok
Lazhar Labiod
Darong Lai
Yuan Lan
Kittichai Lavangnananda
John Lee
Maylor Leung
Peter Lewis
Fuxin Li
Gang Li
Hualiang Li
Jie Li
Ming Li
Sujian Li
Xiaosong Li
Yu-feng Li
Yujian Li
Sheng-Fu Liang
Shu-Hsien Liao
CheePeng Lim
Bingquan Liu
Caihui Liu
Jun Liu
Xuying Liu
Zhiyong Liu
Hung-Yi Lo
Huma Lodhi
Gabriele Lombardi
Qiang Lu
Cuiju Luan
Abdelouahid Lyhyaoui
Bingpeng Ma
Zhiguo Ma
Laurens Van Der Maaten
Singo Mabu
Shue-Kwan Mak
Asawin Meechai
Limin Meng
Komatsu Misako
Alberto Moraglio
Morten Morup
Mohamed Nadif
Kenji Nagata
Quang Long Ngo
Phuong Nguyen
Dan Nie
Kenji Nishida
Chakarida Nukoolkit
Robert Oates
Takehiko Ogawa
Zeynep Orman
Jonathan Ortigosa-Hernandez
Mourad Oussalah
Takashi J. Ozaki
Neyir Ozcan
Pan Pan
Paul S. Pang
Shaoning Pang
Seong-Bae Park
Sunho Park
Sakrapee Paul
Helton Maia Peixoto
Yong Peng
Jonas Peters
Somnuk Phon-Amnuaisuk
J.A.Fernandez Del Pozo
Santitham Prom-on
Lishan Qiao
Yuanhua Qiao
Laiyun Qing
Yihong Qiu
Shah Atiqur Rahman
Alain Rakotomamonjy
Leon Reznik
Nicoleta Rogovschi
Alfonso E. Romero
Fabrice Rossi
Gain Paolo Rossi
Alessandro Rozza
Tomasz Rutkowski
Nishimoto Ryunosuke
Murat Saglam
Treenut Saithong
Chunwei Seah
Lei Shi
Katsunari Shibata
A. Soltoggio
Bo Song
Guozhi Song
Lei Song
Ong Yew Soon
Liang Sun
Yoshinori Takei
Xiaoyang Tan
Chaoying Tang
Lei Tang
Le-Tian Tao
VIII
Jon Timmis
Yohei Tomita
Ming-Feng Tsai
George Tsatsaronis
Grigorios Tsoumakas
Thomas Villmann
Deng Wang
Frank Wang
Jia Wang
Jing Wang
Jinlong Wang
Lei Wang
Lu Wang
Ronglong Wang
Shitong Wang
Shuo Wang
Weihua Wang
Weiqiang Wang
Xiaohua Wang
Xiaolin Wang
Yuanlong Wang
Yunyun Wang
Zhikun Wang
Yoshikazu Washizawa
Bi Wei
Kong Wei
Yodchanan Wongsawat
Ailong Wu
Jiagao Wu
Jianxin Wu
Qiang Wu
Si Wu
Wei Wu
Wen Wu
Bin Xia
Chen Xie
Zhihua Xiong
Bingxin Xu
Weizhi Xu
Yang Xu
Xiaobing Xue
Dong Yang
Wei Yang
Wenjie Yang
Zi-Jiang Yang
Tianfang Yao
Nguwi Yok Yen
Florian Yger
Chen Yiming
Jie Yin
Lijun Yin
Xucheng Yin
Xuesong Yin
JihoYoo
Washizawa Yoshikazu
Motohide Yoshimura
Hongbin Yu
Qiao Yu
Weiwei Yu
Ying Yu
Jeong-Min Yun
Zeratul Mohd Yusoh
Yiteng Zhai
Biaobiao Zhang
Danke Zhang
Dawei Zhang
Junping Zhang
Kai Zhang
Lei Zhang
Liming Zhang
Liqing Zhang
Lumin Zhang
Puming Zhang
Qing Zhang
Rui Zhang
Tao Zhang
Tengfei Zhang
Wenhao Zhang
Xianming Zhang
Yu Zhang
Zehua Zhang
Zhifei Zhang
Jiayuan Zhao
Liang Zhao
Qi Zhao
Qibin Zhao
Xu Zhao
Haitao Zheng
Guoqiang Zhong
Wenliang Zhong
Dong-Zhuo Zhou
Guoxu Zhou
Hongming Zhou
Rong Zhou
Tianyi Zhou
Xiuling Zhou
Wenjun Zhu
Zhanxing Zhu
Fernando José Von Zube
IX
Venue Information
2011 International Conference on Neural Information Processing (ICONIP 2011) will be held at
Majesty Plaza in Shanghai, China from November 13th to 17th, 2011. The hotel is located at 700
Jiujiang Road, Shanghai.
Majesty Plaza
1
ICO
NIP
2011
Tec
hn
ical
Pro
gram
at
a G
lan
ce
Reg
istra
tion
Site
: 1st
Flo
or (0
9:00
-18:
00, N
ov. 1
3th)
, 5th
Flo
or (0
8:00
-18:
00, N
ov. 1
4th-
16th
)
Dat
e T
ime
Roo
m: M
arse
ille
s H
all
Roo
m: S
ydne
y H
all
November 13th
10:0
0-12
:00
Dav
id C
ai: C
ompu
tatio
nal M
odel
ing
of P
rim
ary
Vis
ual C
orte
x H
ang
Li:
Lea
rnin
g to
Ran
k
12:0
0-13
:30
Lun
ch (
2F, M
ajes
ty P
laza
)
13:3
0-15
:30
Pei
-Ji L
iang
: Vis
ual I
nfor
mat
ion
Pro
cess
ing
in R
etin
al N
euro
ns
Irw
in K
ing:
Bas
ics
and
Adv
ance
s in
Sem
i-su
perv
ised
Lea
rnin
g
16:0
0-18
:00
Sha
nfen
g Z
hu &
Hir
oshi
Mam
itsuk
a : D
ata
Min
ing-
base
d A
ppro
ach
for
Dru
g-T
arge
t Pre
dict
ion
Min
g Z
hou
: Sem
antic
Ana
lysi
s an
d S
earc
h of
Tw
itter
and
Chi
nese
Wei
bo
November 14th
08:0
0-8:
15
O
pen
ing
Cer
emon
y (B
anqu
et A
Hal
l, 5F
, Maj
esty
Pla
za)
08:1
5-9:
15
Key
not
e S
pee
ch:
Pro
f. S
hun-
ichi
Am
ari,
Sta
ble
and
Fas
t Dec
isio
n by
Neu
ral N
etw
orks
: Fun
dam
enta
l Pro
blem
s in
Mat
hem
atic
al N
euro
scie
nce
09:1
5-10
:15
Ple
nar
y T
alk:
Pro
f. K
unih
iko
Fuk
ushi
ma,
Rec
ent A
dvan
ces
in th
e N
eoco
gnit
ron:
Rob
ust R
ecog
niti
on o
f V
isua
l Pat
tern
s
10:1
5-10
:45
Cof
fee
Bre
ak
Roo
m: M
arse
ille
s H
all
Roo
m: S
ydne
y H
all
Roo
m: L
eeds
Hal
l R
oom
: Vie
nna
Hal
l R
oom
: Lyo
n H
all
10:4
5-12
:00
Ses
sion
MM
A:
Spe
ech
and
Aud
itory
Pro
cess
ing
Ses
sion
MM
B:
Nat
ural
Lan
guag
e P
roce
ssin
g &
Inte
llig
ent W
eb I
nfor
mat
ion
Pro
cess
ing
Ses
sion
MM
C:
Bio
-Med
ical
Dat
a
Ana
lysi
s
Ses
sion
MM
D:
Neu
ral C
odin
g an
d L
earn
ing
Ses
sion
MM
E:
Bra
in-R
ealis
tic M
odel
s fo
r
Lea
rnin
g, M
emor
y &
Em
bodi
ed C
ogni
tion
12:0
0-13
:30
Lun
ch (
2F, M
ajes
ty P
laza
)
13:3
0-14
:30
Ple
nar
y T
alk:
Pro
f. L
ei X
u,A
utom
atic
Mod
el S
elec
tion
Dur
ing
Lea
rnin
g: A
Com
para
tive
Ove
rvie
w
14:3
0-15
:30
Ple
nar
y T
alk:
Pro
f. S
oo-Y
oung
Lee
, Im
plic
it I
nten
tion
Rec
ogni
tion
& H
iera
rchi
cal K
now
ledg
e D
evel
opm
ent f
or A
rtif
icia
l Cog
niti
ve S
yste
ms
2
15:3
0-16
:00
Cof
fee
Bre
ak
Roo
m: M
arse
ille
s H
all
Roo
m: S
ydne
y H
all
Roo
m: L
eeds
Hal
l R
oom
: Vie
nna
Hal
l R
oom
: Lyo
n H
all
16:0
0-18
:00
Ses
sion
MA
A:
Imag
e P
roce
ssin
g
Ses
sion
MA
B:
Bio
logi
cally
Ins
pire
d V
isio
n an
d R
ecog
nitio
n
Ses
sion
MA
C:
Ker
nel M
etho
ds
Ses
sion
MA
D:
Uns
uper
vise
d L
earn
ing
and
S
elf-
Org
aniz
atio
n
Ses
sion
MA
E:
Neu
ral N
etw
ork
Mod
els
and
App
lica
tion
s
November 15th
08:0
0-09
:00
Ple
nar
y T
alk:
Pro
f. A
ike
Guo
, Dop
amin
e re
veal
s ne
ural
cir
cuit
mec
hani
sms
of v
alue
bas
ed d
ecis
ion
mak
ing
in f
ruit
fly’
s br
ain
09:0
0-10
:00
Ple
nar
y T
alk:
Pro
f. D
eLia
ng W
ang,
A
Cla
ssif
icat
ion
App
roac
h to
the
Coc
ktai
l Par
ty P
robl
em
10:0
0-10
:30
Cof
fee
Bre
ak
Roo
m: M
arse
ille
s H
all
Roo
m: S
ydne
y H
all
Roo
m: L
eeds
Hal
l R
oom
: Vie
nna
Hal
l R
oom
: Lyo
n H
all
10:3
0-12
:00
Ses
sion
TM
A:
Com
puta
tiona
l-In
telli
gent
Hum
an
Com
pute
r In
tera
ctio
n
Ses
sion
TM
B:
Hum
an-O
rigi
nate
d D
ata
Ana
lysi
s an
d Im
plem
enta
tion
Ses
sion
TM
C:
Cli
ffor
d A
lgeb
raic
Neu
ral
Net
wor
ks
Ses
sion
TM
D:
Mul
ti-A
gent
Sys
tem
s
Ses
sion
TM
E:
Sup
ervi
sed
Lea
rnin
g
12:0
0-13
:30
Lun
ch (
2F, M
ajes
ty P
laza
)
13:3
0-14
:30
Ple
nar
y T
alk:
Pro
f. D
eron
g L
iu, S
elf-
Lea
rnin
g C
ontr
ol o
f N
onlin
ear
Sys
tem
s ba
sed
on I
tera
tive
Ada
ptiv
e D
ynam
ic P
rogr
amm
ing
App
roac
h
14:3
0-15
:30
Ple
nar
y T
alk:
Pro
f. J
un W
ang,
The
Sta
te o
f th
e A
rt o
f N
euro
dyna
mic
Opt
imiz
atio
n
15:3
0-16
:00
Cof
fee
Bre
ak
Roo
m: M
arse
ille
s H
all
Roo
m: S
ydne
y H
all
Roo
m: L
eeds
Hal
l R
oom
: Vie
nna
Hal
l R
oom
: Lyo
n H
all
16:0
0-18
:00
Ses
sion
TA
A:
Spik
ing
Neu
rons
Ses
sion
TA
B:
Com
bini
ng M
ultip
le L
earn
ers
Ses
sion
TA
C:
Bra
in S
igna
l Pro
cess
ing
Ses
sion
TA
D:
Com
puta
tiona
l Adv
ance
s in
B
ioin
form
atic
s
Ses
sion
TA
E:
Gra
phic
al a
nd M
ixtu
re
Mod
els
19:0
0-21
:00
Ban
qu
et (
7F, A
sia
Hal
l,X
iao
Nan
Guo
Res
taur
ant,
Sha
ngha
i Int
erna
tiona
l Con
vent
ion
Cen
ter,
2727
, Riv
ersi
de A
venu
e, P
udon
g, S
hang
hai)
* T
he b
uses
for
ban
quet
par
tici
pant
s de
part
ure
Maj
esty
Pla
za a
t 18:
10 to
the
rest
aura
nt a
nd r
etur
n to
the
hote
l fro
m th
e re
stau
rant
at 2
1:30
3
November 16th
08:0
0-09
:00
Ple
nar
y T
alk:
Pro
f. X
in Y
ao, E
volv
ing,
Tra
inin
g an
d D
esig
ning
Neu
ral N
etw
ork
Ens
embl
es
09:0
0-10
:00
Ple
nar
y T
alk:
Pro
f. N
ikol
a K
asab
ov,
Evo
Spi
ke: E
volv
ing
Pro
babi
listic
Spi
king
Neu
ral N
etw
orks
and
Neu
ro-G
enet
ic S
yste
ms
for
Spa
tio-
and
Spe
ctro
-Tem
pora
l
Dat
a M
odel
ling
and
Pat
tern
Rec
ogni
tion
Roo
m: M
arse
ille
s H
all
Roo
m: S
ydne
y H
all
Roo
m: L
eeds
Hal
l R
oom
: Vie
nna
Hal
l R
oom
: Lyo
n H
all
10:3
0-12
:00
S
essi
on W
MA
:
Bra
in-l
ike
Sys
tem
s
Ses
sion
WM
B:
Inte
grat
ing
Mul
tiple
Nat
ure-
insp
ired
App
roac
hes
Ses
sion
WM
C:
Web
and
Doc
umen
t
Pro
cess
ing
Ses
sion
WM
D:
Adv
. in
Com
put.
Inte
llig
ence
Met
hods
Bas
ed P
atte
rn
Rec
ogni
tion
Ses
sion
WM
E:
Bra
in I
mag
ing
and
Bra
in-c
ompu
ter
Inte
rfac
es
12:0
0-13
:30
Lun
ch (
2F, M
ajes
ty P
laza
)
13:3
0-15
:30
Spe
cial
For
um: E
mer
ging
Tec
hnol
ogie
s an
d F
utur
e D
irec
tion
s in
Com
puta
tion
al I
ntel
lige
nce,
Org
aniz
ers:
Jam
es K
wok
and
Liq
ing
Zha
ng;
Mod
erat
or: D
eLia
ng W
ang;
Spe
aker
s: S
hun-
ichi
Am
ari;
Kun
ihik
o F
ukus
him
a; N
ikol
a K
asab
ov; S
oo-Y
oung
Lee
; Der
ong
Liu
; Jun
Wan
g; a
nd X
in Y
ao
15:3
0-17
:30
C
offe
e B
reak
and
Pos
ter
Sess
ion
Nov
embe
r 17
08
:30-
18:3
0
Soci
al P
rogr
am
Rem
arks
: The
ses
sion
ID
con
sist
s of
thre
e le
tter
s, th
e fi
rst l
ette
r st
ands
for
day
, the
sec
ond
lett
er s
tand
s fo
r m
orni
ng (
M)
or a
fter
noon
(A
), a
nd th
e th
ird
lette
r is
the
sequ
ence
labe
l.
For
exa
mpl
e M
AB
sta
nds
for
Mon
day
(M)
+ A
fter
noon
(A)+
Sec
ond
Ses
sion
(B
)
4
Keynotes & Plenary Speakers
Keynote Speech
Stable and Fast Decision by Neural Networks: Fundamental Problems in Mathematical Neuroscience
Shun-ichi Amari
RIKEN Brain Science Institute, Japan
Abstract
The brain, a network consisting of a vast number of neurons, processes information by dynamic interactions of neurons. A neuron receives signals from other neurons and its decision is based on the weighted sum of other signals. Such a decision is called a generalized majority decision. There are many other biological and social systems subject to the generalized majority decision. We search for the fundamental properties of a network of majority decision compared with Boolean logical decision. To this end, we consider a network of randomly connected binary neurons, having 2n states, n the number of neurons. We search for the average number of attractors and the average length of transient periods. We show by using the statistical neurodynamic method that these are extremely small compared to those of a random Boolean network. This is a characteristic feature of a neural network which guarantees quick and reliable decision, because of short transient periods.
We further study dynamics of excitation patterns in a two-dimensional neural field, showing existence of traveling bumps and the way of their control. The collision of traveling bumps shows a possibility of a new style of information processing in a neural field.
Biography
Shun-ichiAmari was born in Tokyo, Japan, on January 3, 1936. He graduated from the Graduate School of the University of Tokyo in 1963 majoring in mathematical engineering and received Dr. Eng. Degree.
He worked as an Associate Professor at Kyushu University and the University of Tokyo, and then a Full professor at the University of Tokyo, and is now Professor-Emeritus. He served as Director of RIKEN Brain Science Institute for five years, and is now its senior advisor. He has been engaged in research in wide areas of mathematical engineering, in particular, mathematical foundations of neural networks, including statistical neurodynamics, dynamical theory of neural fields, associative memory, self-organization, and general learning theory. Another main subject of his research is information geometry initiated by himself, which provides a new powerful method to information sciences and neural networks.
Dr. Amari served as President of Institute of Electronics, Information and Communication Engineers, Japan and President of International Neural Networks Society. He received Emanuel A. Piore Award and Neural Networks Pioneer Award from IEEE, the Japan Academy Award, Gabor Award from INNS, Caianiello Award, and C&C award, among many others.
5
Plenary Talk
Recent Advances in the Neocognitron: Robust Recognition of Visual Patterns
Kunihiko Fukushima
Fuzzy Logic Systems Institute, Japan.
Abstract
The neocognitron is a neural network model proposed by Fukushima (1980). Its architecture was suggested by neurophysiological findings on the visual systems of mammals. It is a hierarchical multi-layered network. It acquires the ability to robustly recognize visual patterns through learning. Although the neocognitron has a long history, modifications of the network to improve its performance are still going on.
In this talk, after a brief introduction of the neocognitron, we discuss several improvements applied recently to the neocognitron.
They are: a) competitive learning with winner-kill-loser rule; b) subtractive inhibition for feature-extracting S-cells, which increases robustness against background noise; c) several methods for extracting oriented edges; d) blurring operation with root-mean-square by C-cells; and so on.
We also show that several new functions can be realized by introducing top-down connections to the neocognitron: a) recognition and completion of partly occluded patterns; b) restoring occluded contours, and so on.
Biography
Kunihiko Fukushima received a B.Eng. degree in electronics in 1958 and a PhD degree in electrical engineering in 1966 from Kyoto University, Japan. He was a professor at Osaka University from 1989 to 1999, at the University of Electro-Communications from 1999 to 2001, at Tokyo University of Technology from 2001 to 2006, and a visiting professor at Kansai University from 2006 to 2010. Prior to his Professorship, he was a Senior Research Scientist at the NHK Science and Technical Research Laboratories. He is now a Senior Research Scientist at Fuzzy Logic Systems Institute.
He is one of the pioneers in the field of neural networks and has been engaged in modeling neural networks of the brain since 1965.
His special interests lie in modeling neural networks of the higher brain functions, especially the mechanism of the visual system.
He was the founding President of JNNS (Japanese Neural Network Society) and a founding member on the Board of Governors of INNS (International Neural Network Society). He is a former President of APNNA (Asia-Pacific Neural Network Assembly).
6
Plenary Talk
Automatic Model SelectionDuringLearning: A Comparative Overview Lei Xu
Chinese University of Hong Kong, Hong Kong
Abstract
A conventional implementation of model selection consists of two stages. One stage enumerates a set of candidate models with the unknown parameters of each candidate estimated by the maximum likelihood learning. The other stage selects the best candidate by one of typical criteria, e.g., AIC, BIC/MDL,HQC. This implementation suffers huge computation and provides unreliable parameter estimation on oversized candidates. One road to tackle this challenge is automatic model selection, i.e., the implementation of a learning principle yields an intrinsic mechanism that drives certain indicators of redundant substructures towards zero, by which these substructures are discarded. This talk makes a comparative overview on several streams of efforts related to this topic in two decades. One consists of heuristic learning rules featured by a mechanism of rival penalized competitive learning and further extensions. Others are Bayesian approaches with help of appropriate priors, including sparse learning, minimum message length, and variational Bayes. Another Bayesian related framework is Bayesian Ying-Yang harmony learning, which is capable of automatic model selection even without imposing priors, and can be further improved with priors incorporated. Empirical comparisons are illustrated on simulated and real datasets for tasks of clustering analyses, image segmentation, speech recognition, and radar target recognition.
Biography
Lei Xu, chair professor of Chinese Univ. Hong Kong (CUHK), Fellow of IEEE (2001-), Fellow of International Association for Pattern Recognition (2002-), and Academician of European Academy of Sciences (2002-). He completed his Ph.D thesis at Tsinghua Univ. by the end of 1986, became postdoc at Peking Univ. in 1987, then promoted to associate professor in 1988 and a professor in 1992. During 1989-93 he was research associate and postdoc in Finland, Canada and USA, including Harvard and MIT. He joined CUHK as senior lecturer in 1993, professor in 1996, and chair professor in 2002. He published several well-cited papers on neural networks, statistical learning, and pattern recognition, e.g., his papers got over 3400 citations (SCI) and over 6300 citations by Google Scholar (GS), with the top-10 papers scored over 2100(SCI) and 4100(GS). One paper scored 790(SCI) and 1351 (GS). He served as a past governor of international neural network society (INNS), a past president of APNNA, and a member of Fellow committee of IEEE CI Society. He received several national and international academic awards (e.g., 1993 National Nature Science Award, 1995 INNS Leadership Award and 2006 APNNA Outstanding Achievement Award).
7
Plenary Talk
Implicit Intention Recognition and Hierarchical Knowledge Development for Artificial Cognitive Systems
Soo-Young Lee
Korea Advanced Institute of Science and Technology, Korea
Abstract
Artificial Cognitive Systems (ACS) is under development based on mathematical models of higher cognitive functions for human-like functions such as vision, auditory, inference, and behaviour. Although the final goal is to provide human-like decision making and behaviour, we are currently focusing on hierarchical knowledge development and recognition of both explicit and implicit human intention. In real world applications these are the core components for robust situation awareness capability, which is directly related to the decision making and behaviour. We propose to utilize multimodal cognitive neuroscience data such as fMRI, EEG, eye gaze, and GSR.
Recognition of human intention is very critical for the awareness of situation involving people. Although current human-machine interfaces have been developed to utilize explicitly-represented human intention such as keystrokes, gesture, and speech, the actual hidden human intention may be different from the explicit one. Also, people may not want to go through tedious processes to present their intentions explicitly, especially for routine sequential tasks and/or sensitive personal situations. Therefore, it is desirable to understand the hidden or unrepresented intention, i.e., 'implicit' intention, for the next-generation intelligent human-oriented user interface. We had measured multimodal signals, i.e., EEG, ECG, GSR, video, and eye gaze signals, while the subjects are asked both obvious and non-obvious questions. The latter includes sensitive personal questions which may incur differences between the explicit and implicit intentions. Also, the subjects made 'Yes' or "No' answer for each question by speech. The measured signals for the obvious questions are regarded as the references, which are used to understand the non-obvious cases. We had separately trained SVM classifiers for each modality from the obvious questions, and tested the SVMs for the non-obvious questions. The agreement (or disagreement) among different modality, and the explicitly-represented intention are analyzed. It demonstrated the possibility of understanding human implicit intention, i.e., classifying into categories, from brain and/or speech signals, which may be utilized as a next-generation human-machine interface.
Biography Soo-Young Lee received B.S., M.S., and Ph.D. degrees from Seoul National University in 1975, Korea Advanced Institute of Science in 1977, and Polytechnic Institute of New York in 1984, respectively. From 1982 to 1985 he also worked for General Physics Corporation at Columbia, MD, USA. In early 1986 he joined the Department of Electrical Engineering, Korea Advanced Institute of Science and Technology. In 1997 he established Brain Science Research Center, which is the main research organization for the Korean Brain Neuroinformatics Research Program from 1998 to 2008. His research interests have resided in Artificial Brain, alias Artificial Cognitive Systems, i.e., the human-like intelligent systems based on biological information processing mechanism in our brain. Especially, he is interested in combining computational neuroscience and information theory for feature extraction, blind signal separation, and top-down attention. He is a Past-President of Asia-Pacific Neural Network Assembly. He received Leadership Award and Presidential Award from International Neural Network Society in 1994 and 2001, respectively, and APPNA Service Award and APNNA Outstanding Achievement Award from Asia-Pacific Neural Network Assembly in 2004 and 2009, respectively. From SPIE he also received Biomedical Wellness Award and ICA Unsupervised Learning Pioneer Award in 2008 and 2010, respectively.
8
Plenary Talk
Dopamine Reveals Neural Circuit Mechanisms of Value Based Decision Making in Fruit Fly’s Brain
Aike Guo
Institute of Neuroscience, SIBS, CAS and Institute of Biophysics, CAS,China.
Abstract
Why fruit Fly’s brain? Drosophila Brain is the geometrical mean between the simplest and the more complicated nervous system. Drosophila transformed developmental genetics and cell biology. Now it is poised to help biologists decipher how the brain works (Claude Desplan, 2007).
Why decision making? "Life is endless series of Decision, regardless of Drosophila or Human beings" to survive, is to make decision. There are two conceptual frameworks of decision-making: simple perception decision and simple value based decision. The neuroeconomics is to explore the brain mechanisms responsible for these evaluative processes, and to explore an animal’s internal valuation of competing alternatives (Sugrue et al., 2005).Here we show that even Drosophila can make clear-cut, salience-based decisions when faced with competing alternatives.
Why mushroom body? Where does the decision making occur in fly’s brain? Mushroom bodies might be the centers of endowing an insect with a degree of “free will”or “intelligent control”over instinctive actions (F.Dujardin, 1850). We found genetic silencing of Mbs impairs decision.
Why Dopamine? The neurotransmitter dopamine (DA) plays a crucial role in motivational control: rewarding, aversive, and alerting (Bromberg-Martin et al, 2010). Using binary expression system: GAL4-Enhancer Trapping & Region-Specific Gene Expression.We revealed that the decision making in Drosophila consists of two phases: an early phase that requiring DA and MB activities and a late phase independent of these activities. Thus, we suggested that the DA-MB circuit regulates salience-based decision making in Drosophila by both gating inhibition and gain-control mechanisms (Zhang et al., 2007; Guo et al., 2009; Guo et al., 2010; Wu and Guo, 2011).
Biography
Dr. Aike Guo,biophysicist and neuroscientist,graduated from Moscow State University, Dept. of Biophysics, in 1965. He received Dr.rer.nat.from Munich University, Germany, in 1979. He has been a visiting scholar funded by Max-Planck-Society in MPI for Biological Cybernetics from 1982 to 1984. He became an academician of the Chinese Academy of Sciences (CAS) in 2003. He is currently a senior investigator and head of the Laboratory of Learning and Memory at Institute of Neuroscience (ION), Shanghai Institutes for Biological Sciences (SIBS), from 1999. He is also a research professor of Institute of Biophysics (IBP), CAS.
During 1979-1992, Dr. Guo has been working in the field of Biophysics, Visual Information Processing and Computational Neuroscience. In the past of 17 years, he has been engaged in the study about the learning and memory using fruit flies (Drosophila) as a model organism from Gene-Brain-Behavior perspective.
His current research interests are focusing in leaning/ memory and visual cognition in Drosophila. His long term goal is to explore the “first principlesof high level cognitive activities in Drosophila brain from an evolutional perspective, to shed new light on the “Brain-Mind Problem.
9
Plenary Talk
A Classification Approach to the Cocktail Party Problem
DeLiang Wang
The Ohio State University, USA
Abstract
The cocktail party problem, also known as the speech segregation problem, has evaded a solution for decades in speech and audio processing. Motivated by recent advances in psychoacoustics and computational auditory scene analysis, I will advocate a new formulation to this old problem: instead of aiming at extracting the target speech, it classifies time-frequency units into two classes: those dominated by the target speech and the rest. This new formulation shifts the emphasis from signal estimation to signal classification, with an important implication that the cocktail party problem is now open to a plethora of binary classification techniques in neural networks and machine learning. I will discuss recent speech segregation algorithms that adopt the binary classification formulation, and the segregation performance of these systems represents considerable progress towards solving the cocktail party problem.
Biography
DeLiang Wang received the B.S. degree in 1983 and the M.S. degree in 1986 from Peking (Beijing) University, Beijing, China, and the Ph.D. degree in 1991 from the University of Southern California, Los Angeles, CA, all in computer science.
From July 1986 to December 1987 he was with the Institute of Computing Technology, Academia Sinica, Beijing. Since 1991, he has been with the Department of Computer Science & Engineering and the Center for Cognitive Science at The Ohio State University, Columbus, OH, where he is a Professor. From October 1998 to September 1999, he was a visiting scholar in the Department of Psychology at Harvard University, Cambridge, MA. From October 2006 to June 2007, he was a visiting scholar at Oticon A/S, Denmark.
Dr. Wang's research interests include machine perception and neurodynamics. Among his recognitions are the Office of Naval Research Young Investigator Award in 1996, the 2005 Outstanding Paper Award from IEEE Transactions on Neural Networks, and the 2008 Helmholtz Award from the International Neural Network Society. He is an IEEE Fellow, and currently serves as Co-Editor-in-Chief of Neural Networks.
10
Plenary Talk
Self-Learning Control of Nonlinear Systems based on Iterative Adaptive Dynamic Programming Approach
Derong Liu
University of Illinois at Chicago, USA
Abstract
Unlike the optimal control of linear systems, the optimal control of nonlinear systems often requires solving the nonlinear Hamilton-Jacobi-Bellman (HJB) equation instead of the Riccati equation. The discrete-time HJB (DTHJB) equation is more difficult to work with than the Riccati equation because it involves solving nonlinear partial difference equations. Though dynamic programming has been an useful computational technique in solving optimal control problems for many years, it is often computationally untenable to run it to obtain the optimal solution, due to the backward numerical process required for its solutions, i.e., the well-known "curse of dimensionality". A self-learning control scheme for unknown nonlinear discrete-time systems with discount factor in the cost function is developed for this purpose. An iterative adaptive dynamic programming algorithm via globalized dual heuristic programming technique is developed to obtain the optimal controller with convergence analysis. Neural networks are used as parametric structures to facilitate the implementation of the iterative algorithm, which will approximate at each iteration the cost function, the optimal control law, and the unknown nonlinear system, respectively. Simulation examples are provided to verify the effectiveness of the present self-learning control approach.
Biography
Derong Liu received the Ph.D. degree in electrical engineering from the University of Notre Dame in 1994. He was a Staff Fellow with General Motors R&D Center, Warren, MI, from 1993 to 1995. He was an Assistant Professor in the Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, from 1995 to 1999. He joined the University of Illinois at Chicago in 1999, where he became a Full Professor of Electrical and Computer Engineering and of Computer Science in 2006. He was selected for the 100 Talents Program by the Chinese Academy of Sciences in 2008. He has published nine books. Dr. Liu is the Editor-in-Chief of the IEEE Transactions on Neural Networks and an Associate Editor of the IEEE Transactions on Control Systems Technology, Neurocomputing and the International Journal of Neural Systems. He was an elected AdCom member of the IEEE Computational Intelligence Society (2006-2008). He received the Harvey N. Davis Distinguished Teaching Award from Stevens Institute of Technology (1997), the Faculty Early Career Development (CAREER) Award from the National Science Foundation (1999), the University Scholar Award from University of Illinois (2006), and the Overseas Outstanding Young Scholar Award from the National Natural Science Foundation of China (2008).
11
Plenary Talk
The State of the Art of Neurodynamic Optimization Jun Wang
Chinese University of Hong Kong, Hong Kong
Abstract
As an important tool for science research and engineering applications, optimization is omnipresent in a wide variety of settings. It is computationally challenging when optimization procedures have to be performed in real time to optimize the performance of dynamical systems. For such applications, classical optimization techniques may not be competent due to the problem dimensionality and stringent requirement on computational time. New paradigms are needed. One very promising approach to dynamic optimization is to apply artificial neural networks. Because of the inherent nature of parallel and distributed information processing in neural networks, the convergence rate of the solution process is not decreasing as the size of the problem increases. This talk will present the state of the art of neurodynamic optimization models and selected applications. Specifically, starting from the motivation of neurodynamic optimization, we will review various recurrent neural network models for optimization. Theoretical results about the stability and optimality of the neurodynamic optimization models will be given along with illustrative examples and simulation results. It will be shown that many computational problems can be readily solved by using the neurodynamic optimization models.
Biography
Jun Wang is a Professor in the Department of Mechanical and Automation Engineering at the Chinese University of Hong Kong. Prior to this position, he held various academic positions at Dalian University of Technology, Case Western Reserve University, and University of North Dakota. He also held various short-term visiting positions at USAF Armstrong Laboratory (1995), RIKEN Brain Science Institute (2001), Universite Catholique de Louvain (2001), Chinese Academy of Sciences (2002), Huazhong University of Science and Technology (2006~007), and Shanghai Jiao Tong University (2008-2011) as a Changjiang Chair Professor. He received a B.S. degree in electrical engineering and an M.S. degree in systems engineering from Dalian University of Technology, Dalian, China. He received his Ph.D. degree in systems engineering from Case Western Reserve University, Cleveland, Ohio, USA. His current research interests include neural networks and their applications. He published about 150 journal papers, 12 book chapters, 10 edited books, and numerous conference papers in these areas. He has been an Associate Editor of the IEEE Transactions on Systems, Man, and Cybernetics Part B since 2003 and a member of the Editorial Advisory Board of the International Journal of Neural System since 2006. He also served as an Associate Editor of the IEEE Transactions on Neural Networks (1999-2009) and IEEE Transactions on Systems, Man, and Cybernetics Part C (2002-2005). He is an IEEE Fellow, an IEEE Distinguished Lecturer, and a recipient of the Outstanding Paper Award for a paper published in the IEEE Transactions on Neural Networks in 2008, Research Excellence Award from the Chinese University of Hong Kong for 2008-2009 and Shanghai Natural Science Award (first class) in 2009.
12
Plenary Talk
Evolving, Training and Designing Neural Network Ensembles Xin Yao
University of Birmingham, UK
Abstract
Combining neural and evolutionary computation has always been an interesting research topic, as learning and evolution are two fundamental forms of adaptation in Nature. Previous work on evolving neural networks has focused on single neural networks. However, monolithic neural networks are often too complex to train or evolve for large and complex problems. It is usually better to design a collection of simpler neural networks that work cooperatively to solve a large and complex problem, which reflects the common problem solving strategy of "divide-and-conquer". The key issue here is how to design such a collection automatically so that it has the best generalisation in learning. This talk introduces some work on evolving neural network ensembles, negative correlation learning, and multi-objective approaches to ensemble learning. The links among different learning algorithms are discussed. Online/incremental learning using ensembles will also be mentioned briefly. Relevant background papers to this talk can be found from http://www.cs.bham.ac.uk/~xin/journal_papers.html.
Biography
Xin Yao is a Professor (Chair) of Computer Science at the University of Birmingham, UK. He is the Director of CERCIA (the Centre of Excellence for Research in Computational Intelligence and Applications), University of Birmingham, UK, and of the Joint USTC-Birmingham Research Institute of Intelligent Computation and Its Applications. He is an IEEE Fellow and a Distinguished Lecturer of IEEE Computational Intelligence Society (CIS). He won the 2001 IEEE Donald G. Fink Prize Paper Award, IEEE Transactions on Evolutionary Computation Outstanding 2008 Paper Award, and many other best paper awards. He was a Changjian Chair Professor, a Distinguished Visiting Professor (Grand Master Chair Professorship) of University of Science and Technology of China (USTC) in Hefei, and a Distinguished Visiting Professor of Yuan Ze University, Taiwan. In his spare time, he volunteered as the Editor-in-Chief (2003.08) of IEEE Transactions on Evolutionary Computation and Vice President for Publications of the IEEE CIS (2009.12). He has been invited to give more than 60 keynote/plenary speeches at international conferences in many different countries. His major research interests include evolutionary computation, neural network ensembles, and their applications. He has more than 350 refereed publications in international journals and conferences.
13
Plenary Talk
EvoSpike: Evolving Probabilistic Spiking Neural Networks and Neuro-Genetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern
Recognition Nikola Kasabov
Auckland University of Technology, New Zealand
Abstract
Spatio- and spectro-temporal data (SSTD) are the most common data in many domain areas, including bioinformatics, neuroinformatics, ecology, environment, medicine, engineering, economics, etc. Still there are no sufficient methods to model such data and to discover complex spatio-temporal patterns from it. The brain is functioning as a spatio-temporal information processing machine and brilliantly deals with spatio-temporal data, thus being a natural inspiration for the development of new methods for SSTD. This research aims at the development of new methods for modeling and pattern recognition of SSTD, called evolving probabilistic spiking neural networks (epSNN), along with their applications.
epSNN are built on the principles of evolving connectionist systems and eSNN in particular and on probabilistic neuronal models. The latter extent the popular leaky integrate-and-fire spiking model with the introduction of some biologically plausible probabilistic parameters. The epSNN are evolving structures that learn and adapt to new incoming data in a fast incremental way.
The presented research explores several approaches to creating epSNN for SSTD, from a single neuron, to reservoir computing and neuro-genetic systems. The presented research explores further ensembles of neurons and neuronal structures that may be called 'reservoirs'. Here they are recurrent SNN that are evolving and deep learning structures, capturing spatial- and temporal components in their interaction and integration.
A main problem in the EvoSpike model and system development is the optimization of numerous parameters. For this purpose three approaches are proposed: using evolutionary computation methods; using a gene regulatory network (GRN) model, or using both in one system, depending on the application.
Biography Professor Nikola Kasabov, FIEEE, FRSNZ is the Director of the Knowledge Engineering and Discovery Research Institute (KEDRI), Auckland. He holds a Chair of Knowledge Engineering at the School of Computing and Mathematical Sciences at Auckland University of Technology. Currently he is an EU FP7 Marie Curie Visiting Professor at the Institute of Neuroinformatics, ETH and University of Zurich. Kasabov is a Past President of the International Neural Network Society (INNS) and also of the Asia Pacific Neural Network Assembly (APNNA). He is a member of several technical committees of IEEE Computational Intelligence Society and a Distinguished Lecturer of the IEEE CIS. He has served as Associate Editor of Neural Networks, IEEE TrNN, IEEE TrFS, Information Science, J. Theoretical and Computational Nanosciences, Applied Soft Computing and other journals. Kasabov holds MSc and PhD from the Technical University of Sofia, Bulgaria. His main research interests are in the areas of neural networks, intelligent information systems, soft computing, bioinformatics, neuroinformatics. He has published more than 450 publications that include 15 books, 130 journal papers, 60 book chapters, 28 patents and numerous conference papers. He has extensive academic experience at various academic and research organisations in Europe and Asia. Prof. Kasabov has received the AUT VC Individual Research Excellence Award (2010), Bayer Science Innovation Award (2007), the APNNA Excellent Service Award (2005), RSNZ Science and Technology Medal (2001), and others. He is an Invited Guest Professor at the Shanghai Jiao Tong University (2010-2012). More information of Prof. Kasabov can be found on the KEDRI web site: http://www.kedri.info
14
ICONIP2011 Technical Program
Mon., Nov. 14
08:00-8:15 Opening Ceremony
Room: Banquet A Hall
Chair: Bao-liang Lu
08:15-9:15
Keynote Speech: Prof. Shun-ichi Amari,
Stable and Fast Decision by Neural Networks:
Fundamental Problems in Mathematical
Neuroscience
Room: Banquet A Hall
Chair: Liqing Zhang
09:15-10:15
Plenary Talk: Prof. Kunihiko Fukushima,
Recent Advances in the Neocognitron: Robust
Recognition of Visual Patterns
Room: Banquet A Hall
Chair: James Kwok
13:30-14:30
Plenary Talk: Prof. Lei Xu,
Automatic Model Selection During Learning:
A Comparative Overview
Room: Banquet A Hall
Chair: Akira Hirose
14:30-15:30
Plenary Talk: Prof. Soo-Young Lee,
Implicit Intention Recognition & Hierarchical
Knowledge Development for Artificial
Cognitive Systems
Room: Banquet A Hall
Chair: Kevin Wong
Tues., Nov. 15
08:00-9:00
Plenary Talk: Prof. Aike Guo,
Dopamine reveals neural circuit mechanisms of
value based decision making in fruit fly’s brain
Room: Banquet A Hall
Chair: Tom Gedeon
09:00-10:00
Plenary Talk: Prof. DeLiang Wang,
A Classification Approach to the Cocktail Party
Problem
Room: Banquet A Hall
Chair: Minho Lee
13:30-14:30
Plenary Talk: Prof. Derong Liu,
Self-Learning Control of Nonlinear Systems
based on Iterative Adaptive Dynamic
Programming Approach
Room: Banquet A Hall
Chair: Irwin King
14:30-15:30
Plenary Talk: Prof. Jun Wang,
The State of the Art of Neurodynamic
Optimization
Room: Banquet A Hall
Chair: Hongtao Lu
Wed., Nov. 16
08:00-9:00
Plenary Talk: Prof. Xin Yao,
Evolving, Training and Designing Neural
Network Ensembles
Room: Banquet A Hall
Chair: Andrew Chi-Sing
Leung
09:00-10:00
Plenary Talk: Prof. Nikola Kasabov,
EvoSpike: Evolving Probabilistic Spiking
Neural Networks and Neuro-Genetic Systems
for Spatio- and Spectro-Temporal Data
Modelling and Pattern Recognition
Room: Banquet A Hall
Chair: Noboru Ohnishi
15
Mon., Nov. 14 MMA: Speech and Auditory Processing,
Room: Marseilles Hall Chair: Shuichi Kurogi
10:45 -11:00 Speaker Identification Using Discriminative
Learning of Large Margin GMM
Khalid Daoudi, Reda Jourani,
Régine André-Obrecht, Driss
Aboutajdine
11:00 -11:15
Preprocessing of Independent Vector Analysis
Using Feed-Forward Network for Robust Speech
Recognition
Myungwoo Oh, Hyung-Min Park
11:15 -11:30
Perfermances Evaluation of GMM-UBM and
GMM-SVM for Speaker Recognition in Realistic
World
Nassim Asbai, Abderrahmane
Amrouche, Mohamed Debyeche
11:30 -11:45 Naive Bayesian Multistep Speaker Recognition
Using Competitive Associative Nets
Shuichi Kurogi,Mineishi Shota,
Tsukazaki Tomohiro, Nishida
Takashi
11:45 -12:00 Modular Scale-Free Function Subnetworks in
Auditory Areas Sanming Song, Hongxun Yao
Mon., Nov. 14
MMB: Natural Language Processing and
Intelligent Web Information Processing,
Room: Sydney Hall
Chair: Rui-Feng Xu
10:45 -11:00 Using Hybrid Kernel Method for Question
Classification in CQA
Shixi Fan, Xiaolong Wang, Xuan
Wang, Xiaohong Yang
11:00 -11:15 News Thread Extraction based on Topical N-gram
Model with a Background Distribution Zehua Yan, Fang Li
11:15 -11:30 Diversifying Question Recommendations in
Community-based Question Answering
Yaoyun Zhang, Xiaolong Wang,
Xuan Wang, Ruifeng Xu, Buzhou
Tang
11:30 -11:45 User Identification for Instant Messages Yuxin Ding, Xuejun Meng,
Guangren Chai, Yan Tang
11:45 -12:00 Towards Understanding Spoken Tunisian Dialect Marwa Graja, Maher Jaoua,
Lamia Hadrich Belguith
Mon., Nov. 14 MMC: Bio-Medical Data Analysis
Room: Leeds Hall Chair: Jie Yang
10:45 -11:00
Dynamic Bayesian Network Modeling of
Cyanobacterial Biological Processes via Gene
Clustering
Nguyen Xuan Vinh, Madhu
Chetty, Ross Coppel , Pramod P.
Wangikar
11:00 -11:15 A Quasi-linear Approach for Microarray Missing
Value Imputation Yu Cheng, Lan Wang, Jinglu Hu
16
11:15 -11:30 Knowledge-based Segmentation of Spine and Ribs
from Bone Scintigraphy
Qiang Wang, Qingqing Chang,
Yu Qiao, Yuyuan Zhu, Gang
Huang, Jie Yang
11:30 -11:45 Adaptive Region Growing Based on Boundary
Measures Yu Qiao, Jie Yang
11:45 -12:00
Exploring Associations Between Changes in
Ambient Temperature and Stroke Occurrence:
Comparative Analysis Using Global and
Personalised Modelling Approaches
Wen Liang, Yingjie Hu, Nikola
Kasabov, Valery Feigin
Mon., Nov. 14 MMD: Neural Coding and Learning
Room: Vienna Hall Chair: Tibor Bosse
10:45 -11:00
Dreaming Your Fear Away: A Computational
Model for Fear Extinction Learning During
Dreaming
Jan Treur
11:00 -11:15 On Rationality of Decision Models Incorporating
Emotion-Related Valuing and Hebbian Learning Jan Treur, Muhammad Umair
11:15 -11:30 Simple Models for Synaptic Information IntegrationDanke Zhang, Yuwei Cui,
Yuanqing Li, Si Wu
11:30 -11:45
A Modified Multiplicative Update Algorithm for
Euclidean Distance-Based Nonnegative Matrix
Factorization and its Global Convergence
Ryota Hibi, Norikazu Takahashi
11:45 -12:00 A Generalized Subspace Projection Approach for
Sparse Representation Classification Bingxin Xu, Ping Guo
Mon., Nov. 14
MME: Brain-Realistic Models for Learning,
Memory and Embodied Cognition
Room: Lyon Hall
Chair: Huajin Tang
10:45 -11:00 Brain Inspired Cognitive System for Learning and
Memory Huajin Tang, Weiwei Huang
11:00 -11:15 Axonal Slow Integration Induced Persistent Firing
Neuron Model
Ning Ning, Kaijun Yi, Kejie
Huang, Luping Shi
11:15 -11:30 A Neuro-Cognitive Robot for Spatial Navigation Weiwei Huang, Huajin Tang, Jiali
Yu, Chin Hiong Tan
11:30 -11:45 Associative Memory Model of Hippocampus CA3
Using Spike Response Neurons
Chin Hiong Tan, Eng Yeow
Cheu, Jun Hu, Qiang Yu, Huajin
Tang
11:45 -12:00 Goal-oriented Behavior Generation for
Visually-guided Manipulation Task
Sungmoon Jeong, Yunjung Park,
Hiroaki Arie, Jun Tani, Minho
Lee
17
Mon., Nov. 14 MAA: Image Processing
Room: Marseilles Hall Chair: Yasuomi D. Sato
16:00 -16:15 A Multimodal Information Collector for
Content-Based Image Retrieval System
He Zhang, Mats Sjöberg, Jorma
Laaksonen, Erkki Oja
16:15 -16:30 Contour-Based Large Scale Image Retrieval Rong Zhou, Liqing Zhang
16:30 -16:45
Multiview Range Image Registration Using
Competitive Associative Net and
Leave-One-Image-Out Cross-Validation Error
Shuichi Kurogi, Tomokazu Nagi,
Shoichi Yoshinaga, Hideaki
Koya, Takeshi Nishida
16:45 -17:00 Airport Detection in Remote Sensing Images Based
on Visual Attention
Xin Wang, Bin Wang, Liming
Zhang
17:00 -17:15 Learning Global and Local Features for License
Plate Detection
Sheng Wang, Wenjing Jia, Qiang
Wu, Xiangjian He, Jie Yang
17:15 -17:30 Integrating Local Features into Discriminative
Graphlets for Scene Classification
Luming Zhang, Wei Bian, Mingli
Song, Dacheng Tao, Xiao Liu
17:30 -17:45 Decision Tree Based Recognition of Bangla Text
from Outdoor Scene Images
Ranjit Ghoshal, Anandarup Roy,
Tapan Kumar Bhowmik, Swapan
K. Parui
17:45 -18:00 A Markov Random Field Model for Image
Segmentation Based on Gestalt Laws
Yuan Ren, Huixuan Tang, Hui
Wei
Mon., Nov. 14
MAB: Biologically Inspired Vision and
Recognition
Room: Sydney Hall
Chair: Jun Miao
16:00 -16:15 Visual Reconstructed Representations for Object
Recognition and Detection
Yasuomi D. Sato, Yasutaka
Kuriya, Christoph von der
Malsburg
16:15 -16:30 Visual Cortex Inspired Junction Detection Shuzhi Sam Ge, Chengyao Shen,
Hongsheng He
16:30 -16:45 Skull-Closed Autonomous Development Yuekai Wang, Xiaofeng Wu,
Juyang Weng
16:45 -17:00 Analysis of The Proton Mediated Feedback Signals
in The Outer Plexiform Layer of Goldfish Retina
Nilton Liuji Kamiji, Masahiro
Yamada, Kazunori Yamamoto,
Hajime Hirasawa, Makoto
Kurokawa, Shiro Usui
17:00 -17:15 Saliency Detection Based on Scale Selectivity of
Human Visual System
Fang Fang, Laiyun Qing, Jun
Miao, Xilin Chen, Wen Gao
17:15 -17:30 A Saliency Detection Model based on Local and
Global Kernel Density Estimation
Huiyun Jing, Xin He, Qi
Han,Xiamu Niu
18
17:30 -17:45 Bio-Inspired Visual Saliency Detection and Its
Application on Image Retargeting
Lijuan Duan, Chunpeng Wu,
Haitao Qiao, Jili Gu, Jun Miao,
Laiyun Qing, Zhen Yang
17:45 -18:00 Effects of Second-Order Statistics on Independent
Component Filters
Andre Cavalcante, Barros Allan
Kardec,Takeuchi Yoshinori,
Ohnishi Noboru
Mon., Nov. 14 MAC: Kernel Methods
Room: Leeds Hall Chair: Mehmet Gonen
16:00 -16:15 Multitask Learning Using Regularized Multiple
Kernel Learning
Mehmet Gönen, Melih Kandemir,
Samuel Kaski
16:15 -16:30 Multi-task Low-rank Metric Learning Based on
Common Subspace
Peipei Yang, Kaizhu Huang,
Cheng-Lin Liu
16:30 -16:45 On Low-Rank Regularized Least Squares for
Scalable Nonlinear Classification
Zhouyu Fu, Guojun Lu, Kai-Ming
Ting, Dengsheng Zhang
16:45 -17:00 Relational Extensions of Learning Vector
Quantization
Barbara Hammer, Frank-Michael
Schleif, Xibin Zhu
17:00 -17:15 Multi-Sphere Support Vector Clustering
Trung Le, Dat Tran, Phuoc
Nguyen, Wanli Ma, Dharmendra
Sharma
17:15 -17:30 Learning with Box Kernels Stefano Melacci, Marco Gori
17:30 -17:45 Solving Support Vector Machines Beyond Dual
Programming Xun Liang
17:45 -18:00 Support Constraint Machines Gori Marco, Melacci Stefano
Mon., Nov. 14
MAD: Unsupervised Learning and
Self-Organization
Room: Vienna Hall
Chair: Kunihiko Fukushima
16:00 -16:15 Neocognitron Trained by Winner-Kill-Loser with
Triple Threshold
Kunihiko Fukushima, Isao
Hayashi, and Jasmin Léveillé
16:15 -16:30 Shape Space Estimation by SOM² Sho Yakushiji, Tetsuo Furukawa
16:30 -16:45 The Self-Organizing Map Tree (SOMT) for
Nonlinear Data Causality Prediction
Younjin Chung, Masahiro
Takatsuka
16:45 -17:00 Simultaneous Pattern and Variable Weighting
During Topological Clustering
Nistor Grozavu and Younes
Bennani
17:00 -17:15 A Robust Approach for Multivariate Binary
Vectors Clustering and Feature Selection
Mohamed Al Mashrgy, Nizar
Bouguila, Khalid Daoudi
19
17:15 -17:30 Co-clustering under Nonnegative Matrix
Tri-Factorization Lazhar Labiod, Mohamed Nadif
17:30 -17:45 A New Simultaneous Two-Levels Coclustering
Algorithm for Behavioural Data-Mining
Guénaël Cabanes, Younès
Bennani, Dominique Fresneau
17:45 -18:00
A Dynamic Unsupervised Laterally Connected
Neural Network Architecture for Integrative Pattern
Discovery
Asanka Fonseka, Damminda
Alahakoon, Jayantha Rajapakse
Mon., Nov. 14
MAE: Neural Network Models and
Applications
Room: Lyon Hall
Chair: John Sum
16:00 -16:15 Self-Adjusting Feature Maps Network Chin-Teng Lin, Dong-Lin Li,
Jyh-Yeong Chang
16:15 -16:30 Analysis On Wang's kWTA with Stochastic Output
Nodes
John Sum, Chi-sing Leung, Kevin
Ho
16:30 -16:45 Method of Solving Combinatorial Optimization
Problems with Stochastic Effects
Takahiro Sota, Yoshihiro
Hayakawa, Shigeo Sato, Koji
Nakajima
16:45 -17:00 Recall Time Reduction of A Morphological
Associative Memory Employing A Reverse Recall Hidetaka Harada, Tsutomu Miki
17:00 -17:15
Robust Control of Nonlinear System Using
Difference Signals and Multiple Competitive
Associative Nets
Shuichi Kurogi, Hiroshi Yuno,
Takeshi Nishida, Weicheng
Huang
17:15 -17:30 An Automated System for The Analysis of The
Status of Road Safety Using Neural Networks Brijesh Verma, David Stockwell
17:30 -17:45 Deep Belief Networks For Financial Prediction Bernardete Ribeiro, Noel Lopes
17:45 -18:00 An Information Theoretic Approach to Joint
Approximate Diagonalization
Matsuda Yoshitatsu, Yamaguchi
Kazunori
Tues., Nov. 15
TMA: Computational-Intelligent Human
Computer Interaction
Room: Marseilles Hall
Chair: Jyh-Yeong Chang
10:30 -10:45 An EEG-Based Brain-Computer Interface for Dual
Task Driving Detection
Chin-Teng Lin,Yu-Kai Wang,
Shi-An Chen
10:45 -11:00 A Sparse Common Spatial Pattern Algorithm for
Brain-Computer Interface
Li-Chen Shi, Yang Li, Rui-Hua
Sun, Bao-Liang Lu
11:00 -11:15 EEG-based Motion Sickness Estimation Using
Principal Component Regression
Li-Wei Ko, Chun-Shu Wei,
Shi-An Chen, Chin-Teng Lin
11:15 -11:30 Reading Your Mind: EEG During Reading Task Tan Vo, Tom Gedeon
11:30 -11:45 A Novel Combination of Time Phase and EEG
Frequency Components for SSVEP-based BCI Jing Jin, Yu Zhang, Xingyu Wang
20
11:45 -12:00 Generalised Support Vector Machine for
Brain-Computer Interface
Trung Le, Dat Tran, Tuan Hoang,
Wanli Ma, Dharmendra Sharma
Tues., Nov. 15
TMB: Human-Originated Data Analysis and
Implementation
Room: Sydney Hall
Chairs: Hyeyoung Park,
Sang-Woo Ban
10:30 -10:45 A Robust Face Recognition through Statistical
Learning of Local Features Jeongin Seo, Hyeyoung Park
10:45 -11:00 Adaptive Colour Calibration for Object Tracking
under Spatially-Varying Illumination Environments
Heesang Shin, Napoleon H.
Reyes, Andre L. Barczak
11:00 -11:15 Expanding Konwledge Source with Ontology
Alignment for Augmented Cognition
Jeong-Woo Son, Seongtaek Kim,
Seong-Bae Park, Yunseok Noh,
Jun-Ho Go
11:15 -11:30 Nyström Approximations for Scalable Face
Recognition: A Comparative Study Jeong-Min Yun, Seungjin Choi
11:30 -11:45 Development of Visualizing Earphone and Hearing
Glasses for Human Augmented Cognition
Byunghun Hwang, Cheol-Su
Kim, Hyung-Min Park, Yun-Jung
Lee, Min-Young Kim, Minho Lee
11:45 -12:00 An Online Human Activity Recognizer for Mobile
Phones with Accelerometer
Yuki Maruno, Kenta Cho, Yuzo
Okamoto, Hisao Setoguchi,
Kazushi Ikeda
Tues., Nov. 15 TMC: Clifford Algebraic Neural Networks
Room: Leeds Hall Chair: Yasuaki Kuroe
10:30 -10:45
Comparison of Complex- and Real-valued
Feedforward Neural Networks in Their
Generalization Ability
Akira Hirose, Shotaro Yoshida
10:45 -11:00 Widely Linear Processing of Hypercomplex Signals Tohru Nitta
11:00 -11:15 An Automatic Music Transcription Based on
Translation of Spectrum and Sound Path EstimationRyota Ikeuchi, Kazushi Ikeda
11:15 -11:30 Real-Time Hand Gesture Recognition Using
Complex-Valued Neural Network (CVNN)
Abdul Rahman Hafiz, Md Faijul
Amin, Kazuyuki Murase
11:30 -11:45
Wirtinger Calculus Based Gradient Descent and
Levenberg-Marquardt Learning Algorithms in
Complex-Valued Neural Networks
Md. Faijul Amin, Muhammad
Ilias Amin, A.Y.H. Al-Nuaimi,
and Kazuyuki Murase
11:45 -12:00 Models of Hopfield-type Cliford Neural Networks
and Their Energy Functions
Yasuaki Kuroe, Shinpei
Tanigawa, Hitoshi Iima
Tues., Nov. 15 TMD: Multi-Agent Systems
Room: Vienna Hall Chair: Yun Li
21
10:30 -10:45 A Computational Agent Model for Hebbian
Learning of Social Interaction Jan Treur
10:45 -11:00 The Bystander Effect: Agent-Based Simulation of
People's Reaction to Norm Violation Charlotte Gerritsen
11:00 -11:15 Multi Agent Carbon Trading Incorporating Human
Traits and Game Theory
Long Tang, Suryani Lim, Madhu
Chetty
11:15 -11:30 Q-Learning with Double Progressive Widening :
Application to Robotics
Nataliya Sokolovska, Olivier
Teytaud, Mario Milone
11:30 -11:45
An Action Selection Method Based on Estimation
of Other's Intention in Time-Varying Multi-Agent
Environments
Kunikazu Kobayashi, Ryu
Kanehira, Takashi Kuremoto,
Masanao Obayashi
11:45 -12:00
Analysis of Beliefs of Survivors of the 7/7 London
Bombings Application of a Formal Model for
Contagion of Mental States
Tibor Bosse, Vikas Chandra, Eve
Mitleton-Kelly, C. Natalie van der
Wal
Tues., Nov. 15 TME: Supervised Learning
Room: Lyon Hall
Chairs: Yoshifusa Ito,
Simone Fiori
10:30 -10:45 Regularizer for Co-existing of Open Weight Fault
and Multiplicative Weight Noise
Chi-Sing Leung, John Pui-Fai
Sum
10:45 -11:00 Uncertainty Measure for Selective Sampling Based
on Class Probability Output Networks
Ho Gyeong Kim, Rhee Man Kil,
Soo-Young Lee
11:00 -11:15 A New Algorithm for Learning Mahalanobis
Discriminant Functions by a Neural Network
Yoshifusa Ito, Hiroyuki Izumi,
Cidambi Srinivasan
11:15 -11:30 An Incremental Class Boundary Preserving
Hypersphere Classifier Noel Lopes, Bernardete Ribeiro
11:30 -11:45 An Extended TopoART Network for the Stable
On-Line Learning of Regression Functions Marko Tscherepanow
11:45 -12:00
Statistical Nonparametric Bivariate Isotonic
Regression by Look-Up-Table-Based Neural
Networks
Simone Fiori
Tues., Nov. 15 TAA: Spiking Neurons
Room: Marseilles Hall Chair: Nikola Kasabov
16:00 -16:15 Evolving Probabilistic Spiking Neural Networks for
Spatio-Temporal Pattern Recognition
Nikola Kasabov, Kshitij Dhoble,
Nuttapod Nuntalid, Ammar
Mohemmed
16:15 -16:30 Event-Driven Simulation of Arbitrary Spiking
Neural Networks on SpiNNaker
Thomas Sharp, Luis A. Plana,
Francesco Galluppi, Steve Furber
16:30 -16:45 Dynamic Response Behaviors of A Generalized
Asynchronous Digital Spiking Neuron Model
Takashi Matsubara, Hiroyuki
Torikai
22
16:45 -17:00 A New Learning Algorithm for Adaptive Spiking
Neural Networks
J Wang, A Belatreche, L.P.
Maguire, T.M. McGinnity
17:00 -17:15 Reservoir-based Evolving Spiking Neural Network
for Spatio-Temporal Pattern Recognition
Stefan Schliebs, Haza Nuzly
Abdull Hamed, Nikola Kasabov
17:15 -17:30
Generalized PWC Analog Spiking Neuron Model
and Reproduction of Fundamental
Neurocomputational Properties
Yutaro Yamashita, Hiroyuki
Torikai
17:30 -17:45 Nonlinear Effect on Phase Response Curve of
Neuron Model
Munenori Iida, Toshiaki Omori,
Toru Aonishi, Masato Okada
17:45 -18:00 Self-organizing Digital Spike Interval Maps Takashi Ogawa, Toshimichi Saito
18:00-18:15 SPAN: A Neuron for Precise-Time Spike Pattern
Association
Ammar Mohemmed, Stefan
Schliebs, Nikola Kasabov
Tues., Nov. 15 TAB: Combining Multiple Learners
Room: Sydney Hall Chair: Nistor Grozavu
16:00 -16:15 Unsupervised Object Ranking Using Not Even
Weak experts
Antoine Cornuéjols, Christine
Martin
16:15 -16:30 Weighted Topological Clustering for Categorical
Data
Nicoleta Rogovschi, Mohamed
Nadif
16:30 -16:45 An Evolutionary Algorithm Based Optimization of
Neural Ensemble Classifiers Chien-Yuan Chiu, Brijesh Verma
16:45 -17:00 Using Bagging and Cross-Validation to Improve
Ensembles Based on Penalty Terms
Joaquín Torres-Sospedra, Carlos
Hernández-Espinosa, Mercedes
Fernández-Redondo
17:00 -17:15 Feature Relationships Hypergraph for Multimodal
Recognition
Luming Zhang, Mingli Song, Wei
Bian , Dacheng Tao, Xiao Liu,
Jiajun Bu, Chun Chen
17:15 -17:30 Energy-Based Feature Selection and Its Ensemble
Version Yun Li, Su-Yan Gao
17:30 -17:45 Improving Boosting Methods by Generating
Specific Training and Validation Sets
Joaquín Torres-Sospedra, Carlos
Hernández-Espinosa, Mercedes
Fernández-Redondo
17:45 -18:00 Predicting Concept Changes Using a Committee of
Experts
Ghazal Jaber, Antoine
Cornuéjols , Philippe Tarroux
Tues., Nov. 15 TAC: Brain Signal Processing
Room: Leeds Hall Chair: Jianting Cao
16:00 -16:15 A Novel Oddball Paradigm for Affective BCIs
using Emotional Faces as Stimuli
Qibin Zhao,Akinari Onishi, Yu
Zhang, Jianting Cao,Liqing
Zhang, Andrzej Cichocki
23
16:15 -16:30
Multiway Canonical Correlation Analysis for
Frequency Components Recognition in
SSVEP-based BCIs
Yu Zhang,Guoxu Zhou,Qibin
Zhao, Akinari Onishi, Jing Jin,
Xingyu Wang, Andrzej Cichocki
16:30 -16:45
An Emotional Face Evoked EEG Signal
Recognition Method Based on Optimal EEG
Feature and Electrodes Selection
Lijuan Duan,Xuebin Wang, Zhen
Yang, Haiyan Zhou, Chunpeng
Wu, Qi Zhang, Jun Miao
16:45 -17:00
Functional Connectivity Analysis with Voxel-based
Morphometry for Diagnosis of Mild Cognitive
Impairment
JungHoe Kim, Jong-Hwan Lee
17:00 -17:15 An Application of Translation Error to Brain Death
Diagnosis Gen Hori, Jianting Cao
17:15 -17:30
Research on Relationship Between Saccadic Eye
Movements and EEG Signals in the Case of Free
Movements and Cued Movements
Arao Funase, Andrzej Cichocki,
and Ichi Takumi
17:30 -17:45
Classification of Multi-spike Trains and Its
Application in Detecting Task Relevant Neural
Cliques
Fanxing Hu, Bao-Ming Li, Hui
Wei
17:45 -18:00
EEG Classification with BSA Spike Encoding
Algorithm and Evolving Probabilistic Spiking
Neural Network
Nuttapod Nuntalid, Kshitij
Dhoble, Nikola Kasabov
Tues., Nov. 15
TAD: Computational Advances in
Bioinformatics
Room: Vienna Hall
Chair: Jonathan H. Chan
16:00 -16:15
Pathway-Based Microarray Analysis with
Negatively Correlated Feature Sets for Disease
Classification
Pitak Sootanan, Santitham
Prom-on, Asawin Meechai, and
Jonathan H. Chan
16:15 -16:30 A Feature Selection Approach for Emulating the
Structure of Mental Representations
Marko Tscherepanow, Marco
Kortkamp, Sina Kühnel, Jonathan
Helbach, Christoph Schütz,
Thomas Schack
16:30 -16:45 A Modified Two-Stage SVM-RFE Model for
Cancer Classification Using Microarray Data
Phit Ling Tan, Shing Chiang Tan,
Chee Peng Lim, Swee Eng Khor
16:45 -17:00
Improved Gene Clustering Based on Particle
Swarm Optimization, K-Means, and Cluster
Matching
Yau-King Lam, P.W.M. Tsang,
Chi-Sing Leung
17:00 -17:15 A Memetic Approach to Protein Structure
Prediction in Triangular Lattices
M.K. Islam, M. Chetty, A. Dayem
Ullah, K. Steinhofel
17:15 -17:30 Personalised Modelling on SNPs Data for Crohn's
Disease Prediction Yingjie Hu, Nikola Kasabov
24
17:30 -17:45 Research on Classification Methods of Glycoside
Hydrolases Mechanism Fan Yang, Lin Wang
17:45 -18:00
The Relationship between the Newborn Rats’
Hypoxic-ischemic Brain Damage and Heart Beat
Interval Information
Xiaomin Jiang, Hiroki Tamura,
Koichi Tanno, Li Yang, Hiroshi
Sameshima, Tsuyomu Ikenoue
Tues., Nov. 15 TAE: Graphical and Mixture Models
Room: Lyon Hall Chair: Kazushi Ikeda
16:00 -16:15 An Infinite Mixture of Inverted Dirichlet
Distributions Taoufik Bdiri and Nizar Bouguila
16:15 -16:30 Polynomial Time Algorithm for Learning Globally
Optimal Dynamic Bayesian Network
Nguyen Xuan Vinh, Madhu
Chetty, Ross Coppel, Pramod P.
Wangikar
16:30 -16:45 Human Activity Inference Using Hierarchical
Bayesian Network in Mobile Contexts Young-Seol Lee, Sung-Bae Cho
16:45 -17:00 Image Classification based on Weighted Topics Yunqiang Liu, Vicent Caselles
17:00 -17:15 Feature Reduction Using a Topic Model for the
Prediction of Type III Secreted Effectors Sihui Qi, Yang Yang, Anjun Song
17:15 -17:30 A Variational Statistical Framework for Object
Detection
Wentao Fan, Nizar Bouguila,
Djemel Ziou
17:30 -17:45 SVM and Greedy GMM Applied on Target
Identification
Dalila Yessad, Abderrahmane
Amrouche, Mohamed Debyeche
17:45 -18:00 Spatial Finite Non-Gaussian Mixture for Color
Image Segmentation Ali Sefidpour, Nizar Bouguila
Wed., Nov. 16 WMA: Brain-like Systems
Room: Marseilles Hall Chair: Minho Lee
10:30 -10:45
Implementation of Visual Attention System Using
Artificial Retina Chip and Bottom-up Saliency Map
Model
Bumhwi Kim, Hirotsugu Okuno,
Tetsuya Yagi, Minho Lee
10:45 -11:00 A Biologically Inspired Model for Occluded
Patterns Saifullah Mohammad
11:00 -11:15 Bio-inspired Model of Spatial Cognition Michal Vavrecka, Igor Farkas,
Lenka Lhotska
11:15 -11:30 Visual Information of Endpoint Position is Not
Required for Prism Adaptation of Shooting Task
Takumi Ishikawa, Yutaka
Sakaguchi
11:30 -11:45 Stable Fast Rewiring Depends on the Activation of
Skeleton Voxels Sanming Song, Hongxun Yao
25
11:45 -12:00 A Method to Construct Visual Recognition
Algorithms on The Basis of Neural Activity Data
Hiroki Kurashige, Hideyuki
Cateau
Wed., Nov. 16
WMB: Integrating Multiple Nature-inspired
Approaches
Room: Sydney Hall
Chair: Xin Yao
10:30 -10:45
Fitness Landscape-based Parameter Tuning Method
for Evolutionary Algorithms for Computing Unique
Input Output Sequences
Jinlong Li, Guanzhou Lu, Xin
Yao
10:45 -11:00 Introducing the Mallows Model on Estimation of
Distribution Algorithms
Josu Ceberio, Alexander
Mendiburu, Jose A. Lozano
11:00 -11:15
A Hybrid Dynamic Multi-objective Immune
Optimization Algorithm Using Prediction Strategy
and Improved Differential Evolution Crossover
Operator
Yajuan Ma, Ruochen Liu,
Ronghua Shang
11:15 -11:30 Alleviate the Hypervolume Degeneration Problem
of NSGA- II Fei Peng, Ke Tang
11:30 -11:45 Optimizing Interval Multi-objective Problems
Using IEAs with Preference Direction
Jing Sun, Dunwei Gong, Xiaoyan
Sun
11:45 -12:00 Evolution of Neural Controllers for Emergence of
Leadership in Robot Colony
Seung-Hyun Lee, Si-Hyuk Yi,
Sung-Bae Cho
Wed., Nov. 16 WMC: Web and Document Processing
Room: Leeds Hall Chair: Irwin King
10:30 -10:45 Topic Modeling of Chinese Language Using
Character-Word Relations
Qi Zhao, Zengchang Qin, Tao
Wan
10:45 -11:00 Enrichment and Reductionism: Two Approaches
for Web Query Classification
Ritesh Agrawal, Xiaofeng Yu,
Irwin King, Remi Zajac
11:00 -11:15
Resource Allocation and Scheduling of Multiple
Composite Web Services in Cloud Computing
Using Cooperative Coevolution
Lifeng Ai, Maolin Tang, Colin
Fidge
11:15 -11:30 PatentRank: An Ontology-based Approach to
Patent Search
Ming Li, Hai-Tao Zheng, Yong
Jiang, Shu-Tao Xia
11:30 -11:45 Learning to Rank Documents Using Similarity
Information between Objects
Di Zhou, Yuxin Ding, Qingzhen
You, Min Xiao
11:45 -12:00 Effect of Dimensionality Reduction on Different
Distance Measures in Document Clustering
Mari-Sanna Paukkeri, Ilkka
Kivimaki, Santosh Tirunagari,
Timo Honkela
26
Wed., Nov. 16
WMD: Advances in Computational
Intelligence Methods based Pattern
Recognition
Room: Vienna Hall
Chairs: Kaizhu Huang; Jun
Sun
10:30 -10:45 Graphical Lasso Quadratic Discriminant Function
for Character Recognition
Bo Xu, Kaizhu Huang, Irwin
King, Cheng-Lin Liua, Jun Sun,
Naoi Satoshi
10:45 -11:00 Learning Based Visibility Measuring with Images
Xu-Cheng Yin, Tian-Tian He,
Hong-Wei Hao, Xi Xu,
Xiao-Zhong Cao, Qing Li
11:00 -11:15 Enhanced Codebook Model for Real-time
Background Subtraction
Munir Shah, Jeremiah Deng,
Brendon Woodford
11:15 -11:30 Multi-View Pedestrian Recognition Using Shared
Dictionary Learning with Group Sparsity
Shuai Zheng, Bo Xie, Kaiqi
Huang, Dacheng Tao
11:30 -11:45 Denial-of-Service Attack Detection Based on
Multivariate Correlation Analysis
Zhiyuan Tan, Aruna Jamdagni,
Xiangjian He, Priyadarsi Nanda,
Ren Ping Liu
11:45 -12:00 A Two Stage Algorithm for K-mode Convolutive
Nonnegative Tucker Decomposition
Qiang Wu, Liqing Zhang, Andrzej
Cichocki
Wed., Nov. 16
WME: Brain Imaging and Brain-computer
Interfaces
Room: Lyon Hall
Chair: Liqing Zhang
10:30 -10:45 A Probabilistic Model for Discovering High Level
Brain Activities from fMRI Jun Li, Dacheng Tao
10:45 -11:00
An Integrated Hierarchical Gaussian Mixture
Model to Estimate Vigilance Level Based on EEG
Recordings
Jing-Nan Gu, Hong-Jun Liu,
Hong-Tao Lu, Bao-Liang Lu
11:00 -11:15 Power Laws for Spontaneous Neuronal Activity in
Hippocampal CA3 Slice Culture
Toshikazu Samura, Yasuomi D.
Sato, Yuji Ikegaya,Hatsuo
Hayashi
11:15 -11:30 Multifractal Analysis of Intracranial EEG in
Epilepticus Rats Tao Zhang, A Kunhan Xu
11:30 -11:45 P300 Response Classification in the Presence of
Magnitude and Latency Fluctuations
Wee Lih Lee, Yee Hong Leung,
Tele Tan
11:45 -12:00 EEG Analysis of the Navigation Strategies in a 3D
Tunnel Task
Michal Vavre cka, Vaclav Gerla,
Lenka Lhotska
27
Wed., Nov. 16
(13:30-15:30)
Special Forum: Emerging Technologies
and Future Directions in Computational
Intelligence
Speakers: Shun-ichi Amari; Kunihiko
Fukushima; Nikola Kasabov; Soo-Young Lee;
Derong Liu; Jun Wang; and Xin Yao
Organizers: James Kwok
and Liqing Zhang;
Moderator: DeLiang Wang
Wed., Nov. 16 WP: Poster Session
15:30-17:30 Learning of Dynamic BNN toward
Storing-and-Stabilizing Periodic Patterns
Ryo Ito, Yuta Nakayama,
Toshimichi Saito
15:30-17:30 Margin Preserving Projection for Image Set Based
Face Recognition
Ke Fan, Wanquan Liu, Senjian
An, Xiaoming Chen
15:30-17:30 A Novel Neural Network for Solving Singular
Nonlinear Convex Optimization Problems
Lijun Liu, Rendong Ge, Pengyuan
Gao
15:30-17:30
Introducing Reordering Algorithms to Classic
Well-known Ensembles to Improve Their
Performance
Joaquín Torres-Sospedra, Carlos
Hernández-Espinosa, Mercedes
Fernández-Redondo
15:30-17:30 Nonlinear Nearest Subspace Classifier Li Zhang, Wei-Da Zhou, Bing Liu
15:30-17:30 A Novel Framework Based on Trace Norm
Minimization for Audio Event Detection
Ziqiang Shi, Jiqing Han, Tieran
Zheng
15:30-17:30 Making Image to Class Distance Comparable Deyuan Zhang, Bingquan Liu,
Chengjie Sun, Xiaolong Wang
15:30-17:30 Co-clustering for Binary Data with Maximum
Modularity Lazhar Labiod, Mohamed Nadif
15:30-17:30 Induction of the Common-sense Hierarchies in
Lexical Data
Julian Szymański, Wlodzislaw
Duch
15:30-17:30 A Novel Synthetic Minority Oversampling
Technique for Imbalanced Data Set Learning
Sukarna Barua, Md. Monirul
Islam, Kazuyuki Murase
15:30-17:30 An Evolutionary Fuzzy Clustering with Minkowski
Distances
Vivek Srivastava, Bipin K
Tripathi, Vinay K Pathak
15:30-17:30 Sparse Coding Image Denoising Based on Saliency
Map Weight Haohua Zhao, Liqing Zhang
15:30-17:30 Fast Growing Self Organizing Map for Text
Clustering
Sumith Matharage, Damminda
Alahakoon, Jayantha Rajapakse,
Pin Huang
15:30-17:30
Introducing a Novel Data Management Approach
for Distributed Large Scale Data Processing In
Future Computer Clouds
Amir H. Basirat, Asad I. Khan
28
15:30-17:30 An Approach to Distance Estimation with Stereo
Vision Using Address-Event-Representation
D. M. M. Jesus, J. F. Angel, P. V.
Rafael, L. T. M. Ramon, C. E.
Elena, L. B. Alejandro, J. M.
Gabriel, M. E. Arturo
15:30-17:30 Estimation System for Human-Interest Degree
while Watching TV Commercials Using EEG
Yuna Negishi, Zhang Dou, Yasue
Mitsukura
15:30-17:30
Modulations of Electric Organ Discharge and
Representation of The Modulations on
Electroreceptors
Kazuhisa Fujita
15:30-17:30 Spiking Neural PID Controllers Andrew Webb, Sergio Davies,
David Lester
15:30-17:30 AER Spiking Neuron Computation on GPUs: the
Frame-to-AER generation
L.T. M. Ramon, D.R. Fernando,
D. M. M. Jesus, J. M. Gabriel, L.
B. Alejandro
15:30-17:30 Enhanced Discrimination of Face Orientation Based
on Gabor Filters
Hyun Ah Song, Sung-do Choi,
Soo-Young Lee
15:30-17:30 Conflict Resolution Based Global Search Operators
for Long Protein Structures Prediction
Md Kamrul Islam, Madhu Chetty,
and Manzur Murshed
15:30-17:30
Comparison Between the Applications of
Fragment-based and Vertex-based GPU
Approaches in K-Means Clustering of Time Series
Gene Expression Data
Yau-King Lam, Wuchao Situ,
P.W.M. Tsang, Chi-Sing Leung,
Yi Xiao
15:30-17:30 EEG-based Emotion Recognition Using Frequency
Domain Features and Support Vector Machines
Xiao-Wei Wang, Dan Nie,
Bao-Liang Lu
15:30-17:30
Research of EEG from Patients with Temporal
Lobe Epilepsy on Causal Analysis of Directional
Transfer Functions
Zhi-Jun Qiu, Hong-Yan Zhang,
Xin Tian
15:30-17:30 Adaptive Classification for Brain-Machine
Interface with Reinforcement Learning
Shuichi Matsuzaki, Yusuke
Shiina, Yasuhiro Wada
15:30-17:30
Person Identification using
Electroencephalographic Signals Evoked by Visual
Stimuli
Jia-Ping Lin, Yong-Sheng Chen,
Li-Fen Chen
15:30-17:30 Medial Axis for 3D Shape Representation Wei Qiu and Ko Sakai
15:30-17:30 Macro Features based Text Categorization Dandan Wang, Qingcai Chen,
Xiaolong Wang, Buzhou Tang
29
15:30-17:30
Univariate Marginal Distribution Algorithm in
Combination with Extremal Optimization
(EO,GEO)
Mitra Hashemi, Mohammad Reza
Meybodi
15:30-17:30 Promoting Diversity in Particle Swarm
Optimization to Solve Multimodal Problems
Shi Cheng, Yuhui Shi, Quande
Qin
15:30-17:30 Analysis of Feature Weighting Methods Based on
Feature Ranking Methods for Classification
Norbert Jankowski, Krzysztof
Usowicz
15:30-17:30
Simultaneous Learning of Instantaneous and
Time-Delayed Genetic Interactions Using Novel
Information Theoretic Scoring Technique
Nizamul Morshed, Madhu Chetty,
Nguyen Xuan Vinh
15:30-17:30 Dynamic Complex-valued Associative Memory
with Strong Bias Terms
Yozo Suzuki, Michimasa Kitahara
and Masaki Kobayashi
15:30-17:30 Describing Human Identity Using Attributes
Zhuoli Zhou, Jiajun Bu, Dacheng
Tao, Luming Zhang, Mingli Song,
Chun Chen
15:30-17:30 Selective Track Fusion Li Xu, Peijun Ma, Xiaohong Su
15:30-17:30
Fast and Incremental Neural Associative Memory
Based Approach for Adaptive Open-loop Structural
Control in High-rise Buildings
Aram Kawewong, Yuji Koike,
Osamu Hasegawa, Fumio Sato
15:30-17:30 Emergence of Purposive and Grounded
Communication through Reinforcement Learning
Katsunari Shibata, Kazuki
Sasahara
15:30-17:30 Support Vector Machines with Weighted
Regularization
Tatsuya Yokota, Yukihiko
Yamashita
15:30-17:30 A Novel Parameter Refinement Approach to One
Class Support Vector Machine
Trung Le, Dat Tran, Wanli Ma,
Dharmendra Sharma
15:30-17:30
Testing Predictive Properties of Efficient Coding
Models with Synthetic Signals Modulated in
Frequency
Fausto Lucena, Mauricio Kugler,
Allan Kardec Barros, Noboru
Ohnishi
15:30-17:30 Utilization of A Virtual Patient Model to Enable
Tailored Therapy for Depressed Patients Fiemke Both, Mark Hoogendoorn
15:30-17:30 Adaptive Detection of Hotspots in Thoracic Spine
from Bone Scintigraphy
Qingqing Chang, Qiang Wang,
Yu Qiao, Yuyuan Zhu, Gang
Huang, Jie Yang
15:30-17:30 ICA-based Automatic Classification of PET Images
From ADNI database
Wenlu Yang, Fangyu He, Xinyun
Chen, Xudong Huang
15:30-17:30 Visual Analytics of Clinical and Genetic Datasets
of Acute Lymphoblastic Leukaemia
Nguyen Quang Vinh,Gleeson
Andrew, Ho Nicholas, Mao
Lin Huang,Simoff Simeon,
Catchpoole Daniel
30
15:30-17:30 Discrimination of Protein Thermostability Based on
a New Integrated Neural Network Jingru Xu,Yuehui Chen
15:30-17:30 Complex Detection Based on Integrated Properties
Yang Yu, Lei Lin,Chengjie
Sun, Xiaolong Wang, Xuan
Wang
15:30-17:30 ECG Classification Using ICA Features and
Support Vector Machines Yang Wu, Liqing Zhang
15:30-17:30 Emotiono: an Ontology with Rule-Based Reasoning
for Emotion Recognition
Xiaowei Zhang, Bin Hu, Philip
Moore, Jing Chen, Lin Zhou
15:30-17:30 An Adaptive Approach to Chinese Semantic
Advertising
Jin-Yuan Chen, Hai-Tao Zheng,
Yong Jiang, Shu-Tao Xia
15:30-17:30 Scalable Data Clustering: A Sammon’s Projection
Based Technique for Merging GSOMs
Hiran Ganegedara, Damminda
Alahakoon
15:30-17:30 The Rough Set-based Algorithm for Two Steps Shu-Hsien Liao, Yin-Ju Chen,
Shiu-Hwei Ho
15:30-17:30 Multi-label Weighted k-Nearest Neighbor Classifier
with Adaptive Weight Estimation Jianhua Xu
15:30-17:30
Parallel Rough Set: Dimensionality Reduction and
Feature Discovery of Multi-Dimensional Data in
Visualization
Tze-Haw Huang, Mao Lin Huang,
Jesse S. Jin
15:30-17:30 Feature Extraction via Balanced Average
Neighborhood Margin Maximization
Xiaoming Chen, Wanquan Liu,
Jianhuang Lai, Ke Fan
15:30-17:30 Document Classification on Relevance: A Study on
Eye Gaze Patterns for Reading
Daniel Fahey, Tom Gedeon,
Dingyun Zhu
15:30-17:30 A Lightweight Ontology LearningMethod for
Chinese Government Documents
Xing Zhao, Hai-Tao Zheng, Yong
Jiang, Shu-Tao Xia
15:30-17:30 Relative Association Rules Based on Rough Set
Theory
Shu-Hsien Liao, Yin-Ju Chen,
Shiu-Hwei Ho
15:30-17:30
15:30-17:30 Use of A Sparse Structure to Improve Learning
Performance of Recurrent Neural Networks
Hiromitsu Awano, Shun Nishide,
Hiroaki Arie, Jun Tani, Toru
Takahashi, Hiroshi G. Okuno,
Tetsuya Ogata
15:30-17:30 Research on A RBF Neural Network in Stereo
Matching
Sheng Xu, Ning Ye, Fa Zhu,
Shanshan Xu, Liuliu Zhou
15:30-17:30 Stability Criterion of Discrete-time Recurrent
Neural Networks with Periodic Delays
Xing Yin, Weigen Wu, Qianrong
Tan
31
15:30-17:30 Improved Global Robust Stability Criteria for
Delayed BAM Neural Networks Xiaolin Li, Ming Liu
15:30-17:30 High Order Hopfield Network with Self-feedback
to Solve Crossbar Switch Problem
Yuxin Ding, Li Dong, Bin Zhao,
Zhanjun Lu
15:30-17:30 Analyzing The Dynamics of Emotional Scene
Sequence Using Recurrent Neuro-Fuzzy Network Qing Zhang, Minho Lee
15:30-17:30 Geometry vs. Appearance for Discriminating
between Posed and Spontaneous Emotions
Ligang Zhang, Dian
Tjondronegoro, Vinod Chandran
15:30-17:30 Towards Learning Inverse Kinematics with A
Neural Network Based Tracking Controller
Tim Waegeman, Benjamin
Schrauwen
15:30-17:30 Color Image Segmentation Based on Blocks
Clustering and Region Growing
Haifeng Sima, Lixiong Liu, Ping
Guo
15:30-17:30 Speed Up Spatial Pyramid Matching Using Sparse
Coding with Affinity Propagation Algorithm Rukun Hu, Ping Guo
15:30-17:30
Analog-Digital Circuit for Motion Detection Based
on Vertebrate Retina and Its Application to Mobile
Robot
Kimihiro Nishio, Taiki Yasuda
15:30-17:30
A Motion Detection Model Inspired by
Hippocampal Function and Its FPGA
Implementation
Haichao Liang, Takashi Morie
15:30-17:30
Intelligent Video Surveillance System Using
Dynamic Saliency Map and Boosted Gaussian
Mixture Model
Wono Lee, Giyoung Lee,
Sang-Woo Ban, Ilkyun Jung,
Minho Lee
15:30-17:30 Recovery of Sparse Signal from An Analog
Network Model
Chi Sing Leung, John Sum,
Ping-Man Lam, A. G.
Constantinides
15:30-17:30 A VLSI Spiking Neural Network with Symmetric
STDP and Associative Memory Operation
Frank L. Maldonado Huayaney,
Hideki Tanaka, Takayuki Matsuo,
Takashi Morie, Kazuyuki Aihara
15:30-17:30 Three Dimensional Surface Temperature
Measurement System
Tao Li, Kikuhito Kawasue,
Satoshi Nagatomo
15:30-17:30 Weber’s Law Based Center-Surround Hypothesis
for Bottom-Up Saliency Detection
Lili Lin, Wenhui Zhou, Hua
Zhang
15:30-17:30 Multi-scale Image Analysis Based on Non-Classical
Receptive Field Mechanism Hui Wei, Qingsong Zuo, Bo Lang
15:30-17:30 A Hybrid FMM-CART Model for Fault Detection
and Diagnosis of Induction Motors
Manjeevan Seera, Chee Peng
Lim, Dahaman Ishak
15:30-17:30 Super Resolution of Text Image by Pruning Outlier Ziye Yan, Yao Lu, JianWu Li
32
15:30-17:30 Opponent and Feedback: Visual Attention Captured
Senlin Wang, Mingli Song,
Dacheng Tao, Luming Zhang,
Jiajun Bu, Chun Chen
15:30-17:30 Depth from Defocus via Discriminative Metric
Learning
Qiufeng Wu, Kuanquan Wang,
Wangmeng Zuo, Yanjun Chen
15:30-17:30 Modeling Manifold Ways of Scene Perception Mengyuan Zhu, Bolei Zhou
15:30-17:30 Dynamic Template Based Online Event Detection Dandan Wang, Qingcai Chen,
Xiaolong Wang, Jiacai Weng
15:30-17:30
Removing Unrelated Features Based on Linear
Dynamical System for Motor-Imagery-Based
Brain-Computer Interface
Jie Wu, Li-Chen Shi, Bao-Liang
Lu
15:30-17:30 Efficient Semantic Kernel-based Text Classification
Using Matching Pursuit KFDA
Qing Zhang, Jianwu Li, Zhiping
Zhang
15:30-17:30 Facial Image Analysis Using Subspace Segregation
Based on Class Information Minkook Cho, Hyeyoung Park
15:30-17:30
A Recurrent Multimodal Network for Binding
Written Words and Sensory-Based Semantics into
Concepts
Andrew P. Papli nski, Lennart
Gustafsson, William M. Mount
15:30-17:30
Recognition of Human’s Implicit Intention Based
on an
Eyeball Movement Pattern Analysis
Young-Min Jang, Sangil Lee,
Rammohan Mallipeddi, Ho-Wan
Kwak, Minho Lee
15:30-17:30 Stress Classification for Gender Bias in Reading Nandita Sharma, Tom Gedeon
15:30-17:30 Vigilance Estimation Based on Statistic Learning
with One ICA Component of EEG Signal Hongbin Yu, Hongtao Lu
15:30-17:30 Multimodal Identity Verification Based on
Learning Face and Gait Cues
S.M.Emdad Hossain, Girija
Chetty