57
Perception: objects in the environment Zsolt Vizi, Ph.D. Robert Bosch Kft. 2018 Perception: objects in the environment Robert Bosch Kft.

Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

  • Upload
    others

  • View
    2

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Perception: objects in the environment

Zsolt Vizi, Ph.D.

Robert Bosch Kft.

2018

Perception: objects in the environment Robert Bosch Kft.

Page 2: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Self-driving cars

Perception: objects in the environment Robert Bosch Kft.

Page 3: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Sensor fusion: one categorization

I Type 1: low-level/raw data fusioncombining several sources of raw data to produce new datathat is expected to be more informative than the inputs.

I Type 2: intermediate-level/feature level fusioncombining various features (e.g. positions) into a featuremap, which can be used for higher level decisions

I Type 3: high-level/decision fusioncombining decisions from several experts (e.g. voting,fuzzy-logic, statistical methods)

Perception: objects in the environment Robert Bosch Kft.

Page 4: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Perception: topics of this lecture

I Object tracking

I Object type classification

Perception: objects in the environment Robert Bosch Kft.

Page 5: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Tracking problems

I The basic tracking problem is to estimate the positionand velocity of the target(s), using the available sensordata (from a sequence of scans).

I The multi-target tracking problem is not simply atracking problem when there are more than one target →problem of associating measurements with targets.

Perception: objects in the environment Robert Bosch Kft.

Page 6: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Tracking problems vs. typical estimation problems

I Strong temporal component is involved.

I Estimation of quantities, which are expected to change overtime.

I Current state is interested.

I Current state is computed from previous states.

Perception: objects in the environment Robert Bosch Kft.

Page 7: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Bayesian inference

I Inference methods consist of estimating the current valuesfor a set of parameters based on a set of observations ormeasurements.

I Bayesian estimation: the parameters are randomvariables that have a prior probability and the observationsare noisy as well

Perception: objects in the environment Robert Bosch Kft.

Page 8: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Recursive Bayesian estimation

Source: http://slidedeck.io/robertsy/ensemble-da

Perception: objects in the environment Robert Bosch Kft.

Page 9: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Bayes theorem

p(x|z) =p(z|x)p(x)

p(z)

I X: target state (random vector variable);

I Z: observation (random vector variable);

I p(x) (probability density function of X): prior density;

I p(x|z): posterior density;

I p(z|x): likelihood function;

I p(z): normalization constant

p(z) =

∫Rnx

p(z|x)p(x) dx

I Notation: p(x, z) = joint density

Perception: objects in the environment Robert Bosch Kft.

Page 10: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Point estimators

In summary: we estimate densities at each steps... How do weuse it in a specific tracking problem? → ’Mapping’ the densityinto real world: point estimator xProcedure

1. Define cost function L(x, x), which defines a penalty for anerroneous estimate x 6= x. Typical choice:

L(x, x) = (x− x)TM(x− x).

2. Bayesian risk R:

R = E (L(x, x)) =

∫Rnx

L(x, x)p(x)dx

Note: x = x(z). Optimal choice:

x(z) = argminx∗(z)

∫Rnx+nz

L(x∗(z), x)p(x, z) dx dz

Perception: objects in the environment Robert Bosch Kft.

Page 11: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Point estimators

In summary: we estimate densities at each steps... How do weuse it in a specific tracking problem? → ’Mapping’ the densityinto real world: point estimator xProcedure

3. Using first derivative, we get [homework]

x(z) = E(x|z)

4. Uncertainity for this estimation:

Pxx = E((x− x)(x− x)T |z)

Perception: objects in the environment Robert Bosch Kft.

Page 12: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Dynamic and sensor model

We focus on first-order Markov processes (current state isdependent only on the previous state).

1. System dynamic model:

xn = fn−1(xn−1) + un + vn−1

I xn: state vector at time tnI fn−1: deterministic transition functionI un: known deterministic controlI vn−1: additive noise

Perception: objects in the environment Robert Bosch Kft.

Page 13: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Dynamic and sensor model

We focus on first-order Markov processes (current state isdependent only on the previous state).

2. Sensor model:zn = hn(xn) + wn

I zn: current observation vectorI hn: deterministic observation functionI wn: additive noise

Simplifying assumption: fn and hn are adiabatic (changing veryslowly in time) → fn = f , hn = h

Perception: objects in the environment Robert Bosch Kft.

Page 14: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Recursive Bayesian filtering

Notation: z1:n = {z1, z2, . . . , zn} (observations up to nth step)Goal: estimating p(xn|z1:n) → applying Bayes theorem:

p(xn|z1:n) =p(z1:n|xn)p(xn)

p(z1:n)

After some calculations, we obtain

p(xn|z1:n) =p (zn|xn) p (xn|z1:n−1)

p (zn|z1:n−1)

Using Chapman-Kolmogorov equation for p (xn|z1:n−1), wederive

p (xn|z1:n−1) =

∫Rnx

p(xn|xn−1)p(xn−1|z1:n−1) dxn−1

Perception: objects in the environment Robert Bosch Kft.

Page 15: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Recursive Bayesian filtering

Perception: objects in the environment Robert Bosch Kft.

Page 16: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Back to the point estimators: a notation

State estimation:xn|p = E{xn|z1:p}

Uncertainity estimation:

Pxxn|p = E

{(xn − xn|p)(xn − xn|p)T |z1:p

}

Perception: objects in the environment Robert Bosch Kft.

Page 17: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Back to the point estimators: prediction

More algebraic manipulation (combining previous formulae,system dynamic model) give:

xn|n−1 =

∫Rnx

{fn−1(xn−1) + un + vn−1} p(xn−1|z1:n−1)dxn−1

and

Pxxn|n−1 =

∫Rnx

{fn−1(xn−1) + un − xn|n−1

}×{

fn−1(xn−1) + un − xn|n−1}T ×

p(xn−1|z1:n−1)dxn−1 +Q,

where Q is the covariance matrix of the system noise:

Q =

∫Rnx

vn−1vTn−1p(xn−1|z1:n−1)dxn−1

Perception: objects in the environment Robert Bosch Kft.

Page 18: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Back to the point estimators: update [by Kalman]

xn|n = Azobsn + b

Assumption:I E(xn − xn|z1:n−1) = 0I E((xn − xn)zobsn |z1:n−1) = 0

Goal #1: Determine A, bSome calculations give

b = xn|n−1 −Azn|n−1and

A = Kn = P xzn|n−1

(P zzn|n−1

)−1which implies

xn|n = xn|n−1 +Kn(zobsn − zn|n−1)P xxn|n = KnP

zzn|n−1K

Tn

Perception: objects in the environment Robert Bosch Kft.

Page 19: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Back to the point estimators: update [by Kalman]

Goal #2: Determine zn|n, Pxzn|n−1, P

zzn|n−1

zn|n =

∫Rnx

{hn(xn) + wn}p(xn|z1:n−1)dxn,

P xzn|n−1 =

∫Rnx

{xn − xn|n−1}{hn(xn)− zn|n−1}T p(xn|z1:n−1)dxn,

P zzn|n−1 =

∫Rnx

{hn(xn)− zn|n−1}{hn(xn)− zn|n−1}T×

p(xn|z1:n−1)dxn +R

where covariance matrix of observation noise is

R =

∫Rnx

wnwTn p(xn|z1:n−1)dxn

Perception: objects in the environment Robert Bosch Kft.

Page 20: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Recursive point estimation process

Perception: objects in the environment Robert Bosch Kft.

Page 21: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Gaussian densities: Kalman filters

I Linear KF: f , h linear

I Extended KF: f , h nonlinear + Taylor approximation

I Finite Difference KF: f , h nonlinear + Stirlingapproximation

I Unscented KF: f , h nonlinear + sigma points: onhypersphere in all directions

I Spherical Simplex KF: f , h nonlinear + sigma points:on intersection of simplex & hypersphere

I Gaussian-Hermite KF: f , h, nonlinear + sigma points:vertices of hypercube

I Monte Carlo KF: f , h nonlinear + MC sampling

Perception: objects in the environment Robert Bosch Kft.

Page 22: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Kalman Filters

Source: https://www.mathworks.com/videos/understanding-kalman-filters-part-1-why-use-kalman-filters–1485813028675.html

Perception: objects in the environment Robert Bosch Kft.

Page 23: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

LKF

System dynamic model:

xn = Fxn−1 + vn−1

Sensor model:zn = Hxn + wn

All densities are Gaussian:

N (x;m,C) =1√

(2π)ndet(C)exp

{−1

2(x−m)C−1(x−m)T )

}

I p(xn|z1:n) = N (xn; xn|n, Pxxn|n)

I p(qn|z1:n−1) = N (qn; qn|n, Pqqn|n−1)

I p(zn) = N (zn; zn|n, Pzzn|n−1)

Perception: objects in the environment Robert Bosch Kft.

Page 24: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

LKF

Using these assumptions, we obtain:

1. Prediction:xn|n−1 = Fxn−1|n−1,

P xxn|n−1 = FP xx

n−1|n−1FT +Q

2. Observation prediction/likelihood:

zn|n−1 = Hxn|n−1,

P zzn|n−1 = HP xx

n|n−1HT +R,

P xzn|n−1 = P xx

n|n−1HT

Perception: objects in the environment Robert Bosch Kft.

Page 25: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

LKF

Using these assumptions, we obtain:

3. Update:

Kn = P xzn|n−1

(P zzn|n−1

)−1xn|n = xn|n−1 +Kn

(zobsn − zn|n−1

),

P xxn|n = P xx

n|n−1 −KnPzzn|n−1K

Tn ,

Perception: objects in the environment Robert Bosch Kft.

Page 26: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

An example [finally...]

State vector:

xn =[pn vn

]=[position velocity

]Constant velocity model:

F =

[1 dt0 1

]System noise:

vn−1 ∼ N (0, Q)

Observation model (sensor output: noisy measurement forposition):

H =[1 0

]Measurement noise:

wn−1 ∼ N (0, σ2)

Perception: objects in the environment Robert Bosch Kft.

Page 27: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

An example [finally...]

(http://david.wf/kalmanfilter/)

Perception: objects in the environment Robert Bosch Kft.

Page 28: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Another example

Simo Sarkka, Bayesian Filtering and Smoothing, CambridgeUnversity Press, 2013

Figure: Chapter 4.3, Example 4.3

Perception: objects in the environment Robert Bosch Kft.

Page 29: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Some words about multi-target tracking problem

I Nearest Neighbors FilterI Probabilistic Data Association FilterI Multihypothesis Filter

More details: http://ais.informatik.uni-freiburg.de/teaching/ws10/robotics2/pdfs/rob2-15-dataassociation.pdf

Perception: objects in the environment Robert Bosch Kft.

Page 30: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Non-Gaussian densities: Particle Filters

Explanation without equations:https://www.youtube.com/watch?v=aUkBa1zMKv4

Tutorial with a bunch of equations:Doucet A., Johansen A.M., A Tutorial on Particle Filtering andSmoothing: Fifteen years later

Perception: objects in the environment Robert Bosch Kft.

Page 31: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

References

1. Anton J. Haug, Bayesian Estimation and Tracking: APractical Guide, Wiley, 2012

2. Sudha Challa et. al, Fundamentals of object tracking,Cambridge University Press, 2011

Perception: objects in the environment Robert Bosch Kft.

Page 32: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Classification problems

The problem of identifying to which of a set of categories(sub-populations) a new observation belongs, on the basis of atraining set of data containing observations (or instances)whose category membership is known.

Perception: objects in the environment Robert Bosch Kft.

Page 33: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Classification problems

I Supervised learning: learning where a training set ofcorrectly identified observations is available (MachineLearning)

I Feature/Explanatory variable/Independentvariable: quantifiable property, which is used in therepresentation of the observation

I Category/Outcome/Dependent variable/Targetvariable/Class/Response variable: e.g.spam/not-spam

I Classifier: classification algorithm

I Binary and multiclass classification: two and moreclasses are involved

Perception: objects in the environment Robert Bosch Kft.

Page 34: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Classification vs. ’estimation’

I Many classifiers output simply the ’best class’ as an answer

I Probabilistic classifiers/estimators return a probability ofthe instance being a member of each of the possible classes→ ’best class’ is naturally the one with the highestprobability

I Advantages of probabilistic methods:I probability = confidence valueI efficient in large-scale problems, because error-propagation

can be avoided

Perception: objects in the environment Robert Bosch Kft.

Page 35: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

General Linear Models

GLMLarge class of models, where the response variable is assumed tofollow an exponential family distribution and this variable is a(typically nonlinear) function of the linear combination offeature values.

Perception: objects in the environment Robert Bosch Kft.

Page 36: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

General Linear Models

Exponential family

p(x) = h(x) exp{ηTT (x)−A(η)

}More details:https://people.eecs.berkeley.edu/ jordan/courses/260-spring10/other-readings/chapter8.pdf

Examples for family members

I Bernoulli distribution: X ∈ {0, 1};P (X = 1) = π

p(x) = πx(1− π)1−x, x ∈ {0, 1}

I Normal distribution

Perception: objects in the environment Robert Bosch Kft.

Page 37: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

General Linear Models

General equation

E(Y ) = g−1(βTX),

where

I X: explanatory variables;

I Y : response variable from an exponentatial familydistribution;

I β: parameter vector;

I g: link function

Perception: objects in the environment Robert Bosch Kft.

Page 38: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

General Linear Models

An example for GLM: linear regression

Model:E(Y ) = β0 + β1x1 + · · ·+ βkxk

Y is normally distributedLink function: g−1(E(Y )) = E(Y ) [identity]

Perception: objects in the environment Robert Bosch Kft.

Page 39: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Logistic regression

I Response variable Y is Bernoulli distributed withparameter π, i.e. the observations can correspond to twoclasses (binary case)→ if Y ∼ Bernoulli(π), then E(Y ) = π.

I X = {X1, X2, . . . , Xk} is the feature vector.I Odds ratio: ratio of π and 1− π, which gives a measure

for comparing class membershipsI Link function: logarithm of odds ratio

g(π) = log

1− π

)I Model:

log

1− π

)= β0 + β1X1 + · · ·+ βkXk

Perception: objects in the environment Robert Bosch Kft.

Page 40: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Logistic regression

Probably more familiar with mean function g−1(βTX):

π =1

1 + exp(−βTX)

Source: https://rcompanion.org/rcompanion/e06.html

Perception: objects in the environment Robert Bosch Kft.

Page 41: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Logistic regression

I We use a training set{X(i), Y (i)

}Ni=1

.

I Goodness of parameter vector = how correctly it works onthe training set ⇐⇒ gap/error is small

I Cost function/Error function/Loss function:measures the error of the estimate, the goal is to minimize

I Classical choice: mean squared error

MSE(β) =1

N

N∑i=1

(Yi − Yi)2

Perception: objects in the environment Robert Bosch Kft.

Page 42: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Logistic regression

I A more convenient cost function now:

CE(β) =− 1

N

N∑i=1

Y (i) log(g−1

(βTX(i)

))− 1

N

N∑i=1

(1− Y (i)) log(

1− g−1(βTX(i)

))Finding optimal parameter vector = minimizing cost function

Perception: objects in the environment Robert Bosch Kft.

Page 43: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Some notes on optimization

Gradient descent

Source: http://charlesfranzen.com/posts/multiple-regression-in-python-gradient-descent/

Perception: objects in the environment Robert Bosch Kft.

Page 44: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Some notes on optimization

Stochastic gradient descent

Source: Andrew Ng, Machine Learning (online course, Coursera)

Perception: objects in the environment Robert Bosch Kft.

Page 45: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Multiclass problem

Possible modifications:

I 1 vs. rest [K classifiers]

I 1 vs. 1 [K(K − 1)/2 classifiers]

I multinominal extension: for logistic regression, introducesoftmax function

πj =exp

(βTj X

)∑K

i=1 exp(βTi X

) ; j = 1, 2, . . . ,K

Perception: objects in the environment Robert Bosch Kft.

Page 46: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Evaluation

Confusion matrix

Source:https://www.packtpub.com/books/content/supervised-learning-classification-and-regressionLiu et. al, Learning accurate and interpretable models based on regularized random forestsregression, doi:10.1186/1752-0509-8-S3-S5

Perception: objects in the environment Robert Bosch Kft.

Page 47: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Evaluation

ROC curve

Source:http://jxieeducation.com/2016-09-27/Attractive-Mathematical-Properties-Of-The-ROC-Curve/

Perception: objects in the environment Robert Bosch Kft.

Page 48: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Naive Bayes classifier

Probabilistic model: the goal is to calculate the probability

p(Cj |x),

where Cj is the correspodence to class j, x = (x1, x2, . . . , xk) isan instance of the feature vector.Approach: Bayes theorem!

p(Ck|x) =p(x|Ck)p(Ck)

p(x)

Condition of ’naivety’: features are conditionallyindependent

p(xi|xi+1, . . . , xk, Cj) = p(xi|Cj)

Perception: objects in the environment Robert Bosch Kft.

Page 49: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Naive Bayes classifier

Using definition of conditional PDFs, law of total probabilityand chain rule, we can derive

p(Cj |x) =p(Cj)

∏ki=1 p(xi|Cj)∑k

i=1 p(Ci)p(x|Cj)

How to classify:

y = argmaxj∈{1,2,...,K}p(Cj)

k∏i=1

p(xi|Cj)

Perception: objects in the environment Robert Bosch Kft.

Page 50: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Naive Bayes-Gauss classifier

Perception: objects in the environment Robert Bosch Kft.

Page 51: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

More general topics (not covered now)

I Bias, variance

I Problem of underfitting/overfitting

I Regularization

I Curse of dimensionality

I Feature engineering

I Model selection (e.g. elimination techniques)

Perception: objects in the environment Robert Bosch Kft.

Page 52: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

More basic classification algorithms

I Decision Tree, Random Forest

I K-nearest neighbors

I Support Vector Machine

Perception: objects in the environment Robert Bosch Kft.

Page 53: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Deep Learning

Artificial Neural Networks

Source: https://www.digitaltrends.com/cool-tech/what-is-an-artificial-neural-network/

Perception: objects in the environment Robert Bosch Kft.

Page 54: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Deep Learning

Artificial Neural Networks

Source: https://www.mathworks.com/discovery/convolutional-neural-network.html

Perception: objects in the environment Robert Bosch Kft.

Page 55: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Deep Learning

Artificial Neural Networks

Source: http://www.flytxt.com/deep-learning-with-recurrent-neural-networks-rnn/

Perception: objects in the environment Robert Bosch Kft.

Page 56: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

References

Online courses

I Kirill Eremenko, Machine Learning (udemy.com)

I Kirill Eremenko, Deep Learning (udemy.com)

I Andrew Ng, Machine Learning (coursera.org)

I Pennsylvania State University, Statistics online(https://onlinecourses.science.psu.edu/statprogram/)

Books

I Christopher Bishop, Pattern Recognition and MachineLearning, Springer, 2011

I Goodfellow et. al, Deep Learning, MIT Press, 2016

Useful links

I https://www.kaggle.com

I https://www.analyticsvidhya.com/

Perception: objects in the environment Robert Bosch Kft.

Page 57: Perception: objects in the environment · (sub-populations) a new observation belongs, on the basis of a training set of data containing observations (or instances) whose category

Thank You For YourAttention!

Perception: objects in the environment Robert Bosch Kft.