Deep Learning – an Overview · Co-Founder & CTO rene.donner@contextflow.com René Donner...

Preview:

Citation preview

Co-Founder & CTOrene.donner@contextflow.com

René Donner

Deep Learning – an Overview

René Donner Deep Learning

Overview

3

The (amazing) things Deep Learning can do

How does it work?

How can you start with DL?

René Donner Deep Learning

Roughly …

4

Deep learning finds patternsin data corresponding tohigh-level, abstract concepts

What can it do?

René Donner Deep Learning

What it can be used for

6

Image recognition

Text understanding, translation

Voice recognition

Playing video games

Driving cars

René Donner Deep Learning

Image recognition

7

René Donner Deep Learning

Scene labeling

8

http://www.purdue.edu/newsroom/releases/2014/Q1/smartphone-to-become-smarter-with-deep-learning-innovation.html

René Donner Deep Learning

Text recognition

9

http://www.pyimagesearch.com/2014/09/22/getting-started-deep-learning-python/

Large-Scale Deep Learning for Intelligent Computer Systems, Jeff Dean, Google, BayLearn 2015

René Donner Deep Learning

Text understanding

10

2013 Glove: Global Vectors for Word Representation, Jeffrey Pennington, Richard Socher and Christopher D. Manning

René Donner Deep Learning

Word embeddings

11

René Donner Deep Learning

Information extraction / Reasoning

12

MetaMind

René Donner Deep Learning

Some well know research groups

13

Stanford / BaiduAndrew Ng

NYU / FacebookYann LeCun

UToronto / GoogleGeoffrey Hinton

René Donner Deep Learning

NVIDIA

14

Images: NVIDIA website

How does it work?

René Donner Deep Learning

Difference to classic ML

16

http://rinuboney.github.io/2015/10/18/theoretical-motivations-deep-learning.html

René Donner Deep Learning

Deep learning

17

http://theanalyticsstore.ie/deep-learning/

René Donner Deep Learning

Visualization

18

1. Layer

higher Layers

Emergence of Object-Selective Features in Unsupervised Feature Learning, Adam Coates, NIPS 2012

René Donner Deep Learning 19

http://theanalyticsstore.ie/deep-learning/ http://stats.stackexchange.com/questions/114385/what-is-the-difference-between-convolutional-neural-networks-restricted-boltzma

René Donner Deep Learning 20

https://medium.com/machine-learning-world/how-to-debug-neural-networks-manual-dc2a200f10f2

René Donner Deep Learning

Optimization

21

Stochastic gradient descent

Automatic differentiation

blog.datumbox.com

René Donner Deep Learning

Local minima

22

Less problematic than thought - saddle points

https://ganguli-gang.stanford.edu/figures/14.Saddlepoint.jpg

René Donner Deep Learning

Deep learning

23

Low level features of color images

https://www.coursera.org/course/neuralnets

René Donner Deep Learning

Deep learning

24

http://www.pamitc.org/cvpr15/files/lecun-20150610-cvpr-keynote.pdf

René Donner Deep Learning

Inception topologies

25

ImageNet Classification with Deep Convolutional Neural Networks", Alex Krizhevsky

“Inception” deep neural network architecture. Source: Christian Szegedy et. al. Going deeper with convolutions. CVPR 2015

René Donner Deep Learning

Network Aims

26

“Inception” deep neural network architecture. Source: Christian Szegedy et. al. Going deeper with convolutions. CVPR 2015

Classification accuracy

Inference speed (e.g. for video)

Size (mobile devices)

Energy per prediction (battery)

René Donner Deep Learning

Model Zoos

27

“Inception” deep neural network architecture. Source: Christian Szegedy et. al. Going deeper with convolutions. CVPR 2015

Readily trained networks

Transfer learning - adapt to your task

ONNX exchange format

René Donner Deep Learning

MNIST - Code Demo

28

René Donner Deep Learning

MNIST

29

http://deeplearning4j.org/rbm-mnist-tutorial.html

René Donner Deep Learning

Deep learning - why does it work?

30

Can cope with huge amounts of data

Learns small invariances

Overcomplete, sparse, representations

Learn Embedding

Lots of data

Recent advance: it is actually computable!

René Donner Deep Learning

Deep learning - pros

31

Not-domain specific

Supervised / Semi-supervised / Unsupervised

Classification / regression in last layer

Simple math

Hip

René Donner Deep Learning

Deep learning - cons

32

Lots of meta-parameters

Needs a lot of data

Very compute intensive

Hip

Getting started with DL

René Donner Deep Learning

Frameworks

34

Many different DL toolboxes

Efficiency important (GPU)

Attention to numerical issues

René Donner Deep Learning

Frameworks

35

Caffehttp://caffe.berkeleyvision.org/Plain text filesFastest CNN, GPU

Kerashttps://github.com/fchollet/kerasPython, on top of Theano

TensorFlowhttp://tensorflow.org/Python, by Google

MXNethttps://github.com/dmlc/mxnetPython, R, Julia

Slid

e fro

m c

affe

tuto

rial

René Donner Deep Learning

Tensorflow

36

General gradient descent library

René Donner Deep Learning

Tutorials

37

Stanford tutorialhttps://deeplearning.stanford.edu/wiki/index.php/UFLDL_TutorialMatlab code snippets

videolectures.nethttp://videolectures.net/deeplearning2015_montreal/

courserahttps://www.coursera.org/course/neuralnets

René Donner Deep Learning

Practical hints

38

Bengio ArxivPractical Recommendations for Gradient-Based Training of Deep Architectureshttp://arxiv.org/abs/1206.5533http://rinuboney.github.io/2015/10/18/theoretical-motivations-deep-learning.html

Kaggle http://www.kaggle.com/c/galaxy-zoo-the-galaxy-challengehttp://benanne.github.io/2014/04/05/galaxy-zoo.html

Relevant conferences NIPS (https://sites.google.com/site/deeplearningworkshopnips2013/accepted-papers)CVPR, ICMLMany interesting papers on arxiv.org

René Donner Deep Learning

Current research topics

39

Parallelization

What is deep learning, actually?

Alternative, faster, simpler methods

Multi-domain, transfer learning

Generative Adversarial Networks (GANs)

Co-Founder & CTOrene.donner@contextflow.com

René Donner

Deep Learning – an Overview

Recommended