Artificial Intelligent

Neural Networks

Nguyen Van Vinh

UET-VNU

1
 Outline
• Neural Networks
• Backpropagation
• Demo

2
NEURAL NETWORKS

3
Learning highly non-linear functions
f: X  Y
 f might be non-linear function
 X (vector of) continuous and/or discrete vars
 Y (vector of) continuous and/or discrete vars

The XOR gate Speech recognition

© Eric Xing @ CMU, 2006-2011 4

Perceptron and Neural Nets
 From biological neuron to artificial neuron (perceptron)
Synapse Inputs
Synapse Dendrites x1 Linear Hard
Axon
Axon w1 Combiner Limiter
Output
 Y
Soma Soma w2
Dendrites 
x2
Synapse
Threshold
 Activation function
n
 1, if X  
X   xi wi Y 
i 1  1, if X  

 Artificial neuron networks

 supervised learning

Out put Signals

Input Signals
 gradient descent

Middle Layer
Input Layer Output Layer
© Eric Xing @ CMU, 2006-2011 5
Connectionist Models
 Consider humans:
 Neuron switching time
~ 0.001 second
 Number of neurons
~ 1010
 Connections per neuron
~ 104-5
 Scene recognition time
~ 0.1 second
 100 inference steps doesn't seem like enough
 much parallel computation
 Properties of artificial neural nets (ANN)
 Many neuron-like threshold switching units
 Many weighted interconnections among units
 Highly parallel, distributed processes

© Eric Xing @ CMU, 2006-2011 6

 Why is everyone talking
Motivation
about Deep Learning?
• 2016: year of deep learning

7
 Why is everyone talking
Motivation
about Deep Learning?

8
 Why is everyone talking
Motivation
about Deep Learning?
• Because a lot of money is invested in it…
– DeepMind: Acquired by Google for $400
million
– DNNResearch: Three person startup
(including Geoff Hinton) acquired by Google
for unknown price tag
– Enlitic, Ersatz, MetaMind, Nervana, Skylab:
Deep Learning startups commanding millions
of VC dollars
• Because it made the front page of the
New York Times
9
Motivation Why Deep Learning?

10
Motivation Why now?

2006

2016

11
 A Recipe for
Background
Machine Learning
1. Given training data: Face Face Not a face

2. Choose each of these:

– Decision function
Examples: Linear regression,
Logistic regression, Neural Network

– Loss function
Examples: Mean-squared error,
Cross Entropy

12
 A Recipe for
Background
Machine Learning
1. Given training data: 3. Define goal:

2. Choose each of these:

– Decision function 4. Train with SGD:
(take small steps
opposite the gradient)
– Loss function

13
 A Recipe for
Background
Gradients
Machine Learning
1. Given training data: 3. Definecan
Backpropagation goal:
compute this
gradient!
And it’s a special case of a more
general algorithm called reverse-
2. Choose each of these:mode automatic differentiation that
– Decision function can compute
4. Train
the with SGD:
gradient of any
differentiable
(takefunction efficiently!
small steps
opposite the gradient)
– Loss function

14
 A Recipe for
Background
Goals for this lecture
Machine Learning
1. 1.
Given training
Explore data:
a new class of 3. Define functions
decision goal:
(Neural Networks)
2. Consider variants of this recipe for training
2. Choose each of these:
– Decision function 4. Train with SGD:
(take small steps
opposite the gradient)
– Loss function

15
Decision Functions Linear Regression

Output

θ1 θ2 θ3 θM

Input …
16
Decision Functions Logistic Regression

Output

θ1 θ2 θ3 θM

Input …
17
Decision Functions Logistic Regression

Output

Face Face Not a face

θ1 θ2 θ3 θM

Input …
18
Decision Functions Logistic Regression

Output

1 1 0

y
x2
θ1 θ2 θ3 θM
x1

Input …
19
Decision Functions Logistic Regression

Output

θ1 θ2 θ3 θM

Input …
20
The Perceptron: Forward Propagation

21
Neural Network Model
Inputs
.6 Output
Age 34 .4
.2 S
.1 .5 0.6
Gender 2 .3 .2
.8
S
.7 S “Probability of
beingAlive”
Stage 4 .2

Dependent
Independent Weights HiddenL Weights variable
variables ayer
Prediction

© Eric Xing @ CMU, 2006-2011 22

“Combined logistic models”
Inputs
.6 Output
Age 34
.5 0.6
.1
Gender 2 S
.7 .8 “Probability of
beingAlive”
Stage 4

Dependent
Independent Weights HiddenLayer Weights variable
variables
Prediction

© Eric Xing @ CMU, 2006-2011 23

 Inputs
Output
Age 34
.2 .5
0.6
Gender 2 .3
S
“Probability of
.8
beingAlive”
Stage 4 .2

Dependent
Independent Weights HiddenL Weights variable
variables ayer
Prediction

© Eric Xing @ CMU, 2006-2011 24

 Inputs
.6 Output
Age 34
.2 .5
.1 0.6
Gender 1 .3
S
.7 “Probability of
.8
beingAlive”
Stage 4 .2

Dependent
Independent Weights HiddenL Weights variable
variables ayer
Prediction

© Eric Xing @ CMU, 2006-2011 25

Not really,
no target for hidden units...

Age 34 .6 .4
.2 S
.1 .5 0.6
Gender 2 .3 .2
.8
S
.7 S “Probability of
beingAlive”
Stage 4 .2

Dependent
Independent Weights HiddenL Weights variable
variables ayer
Prediction

© Eric Xing @ CMU, 2006-2011 26

Jargon Pseudo-Correspondence
 Independent variable = input variable
 Dependent variable = output variable
 Coefficients = “weights”
 Estimates = “targets”

Logistic Regression Model (the sigmoid unit)

Inputs Output
Age 34
5
0.6
Gende 1 4
S “Probability of
r beingAlive”
Stage 4 8

Independent variables Coefficients Dependent variable

x1, x2, x3 a, b, c p Prediction
© Eric Xing @ CMU, 2006-2011 27
Decision Functions Neural Network

Output

Hidden Layer …

Input …
28
Decision Functions Neural Network

Output

…
Hidden Layer

…
Input

29
 Building a Neural Net

Output

Features …

30
 Building a Neural Net

Output

Hidden Layer …
D=M

1 1 1

Input …
31
 Building a Neural Net

Output

Hidden Layer …
D=M

Input …
32
 Building a Neural Net

Output

Hidden Layer …
D=M

Input …
33
 Building a Neural Net

Output

Hidden Layer …
D<M

Input …
34
 Decision Boundary

• 0 hidden layers: linear classifier

– Hyperplanes

x1 x2

Example from to Eric Postma via Jason Eisner 35

 Decision Boundary

• 1 hidden layer
– Boundary of convex region (open or closed)

x1 x2

Example from to Eric Postma via Jason Eisner 36

 Decision Boundary

y
• 2 hidden layers
– Combinations of convex regions

x1 x2

Example from to Eric Postma via Jason Eisner 37

Decision Functions Multi-Class Output

Output …

Hidden Layer …

Input …
38
Decision Functions Deeper Networks

Next lecture:

Output

…
Hidden Layer 1

…
Input

39
Decision Functions Deeper Networks

Next lecture:

Output

…
Hidden Layer 2

…
Hidden Layer 1

…
Input

40
Decision Functions Deeper Networks

Next Output

lecture:
…
Making the Hidden Layer 3

neural
networks Hidden Layer 2
…

deeper
…
Hidden Layer 1

…
Input

41
Decision Functions Different Levels of Abstraction

• We don’t know
the “right”
levels of
abstraction
• So let the model
figure it out!

42
Example from Honglak Lee (NIPS 2010)
Decision Functions Different Levels of Abstraction

Face Recognition:
– Deep Network
can build up
increasingly
higher levels of
abstraction
– Lines, parts,
regions

43
Example from Honglak Lee (NIPS 2010)
Decision Functions Different Levels of Abstraction
Output

…
Hidden Layer 3

…
Hidden Layer 2

…
Hidden Layer 1

…
Input

44
Example from Honglak Lee (NIPS 2010)
ARCHITECTURES

45
 Neural Network Architectures
Even for a basic Neural Network, there are many design
decisions to make:
1. # of hidden layers (depth)
2. # of units per hidden layer (width)
3. Type of activation function (nonlinearity)
4. Form of objective function

46
 Activation Functions
Neural Network with sigmoid
activation functions

Output

…
Hidden Layer

…
Input

47
 Activation Functions
Neural Network with arbitrary
nonlinear activation functions

Output

…
Hidden Layer

…
Input

48
 Activation Functions
Sigmoid / Logistic Function So far, we’ve
1 assumed that the
logistic(u) º -u activation function
1+ e
(nonlinearity) is
always the sigmoid
function…

49
 Activation Functions
• A new change: modifying the nonlinearity
– The logistic is not widely used in modern ANNs

Alternate 1:
tanh

Like logistic function but

shifted to range [-1, +1]

Slide from William Cohen

 Activation Functions
• A new change: modifying the nonlinearity
– reLU often used in vision tasks

Alternate 2: rectified linear unit

Linear with a cutoff at zero

(Implementation: clip the gradient

when you pass zero)

Slide from William Cohen

 Activation Functions
• A new change: modifying the nonlinearity
– reLU often used in vision tasks

Alternate 2: rectified linear unit

Soft version: log(exp(x)+1)

Doesn’t saturate (at one end)

Sparsifies outputs
Helps with vanishing gradient

Slide from William Cohen

 Objective Functions for NNs
• Regression:
– Use the same objective as Linear Regression
– Quadratic loss (i.e. mean squared error)
• Classification:
– Use the same objective as Logistic Regression
– Cross-entropy (i.e. negative log likelihood)
– This requires probabilities, so we add an additional
“softmax” layer at the end of our network

53
 Multi-Class Output

Output …

Hidden Layer …

Input …
54
 Multi-Class Output
Softmax:

…
Output

…
Hidden Layer

…
Input

55
 Cross-entropy vs. Quadratic loss

Figure from Glorot & Bentio (2010)

 A Recipe for
Background
Machine Learning
1. Given training data: 3. Define goal:

2. Choose each of these:

– Decision function 4. Train with SGD:
(take small steps
opposite the gradient)
– Loss function

57
BACKPROPAGATION

58
 A Recipe for
Background
Machine Learning
1. Given training data: 3. Define goal:

2. Choose each of these:

– Decision function 4. Train with SGD:
(take small steps
opposite the gradient)
– Loss function

59
Training Backpropagation

• Question 1:
When can we compute the gradients of the parameters of
an arbitrary neural network?

• Question 2:
When can we make the gradient computation efficient?

60
Training Chain Rule

Given:
Chain Rule:

61
Training Chain Rule

Given:
Chain Rule:

Backpropagation
…
is just repeated
application of the
chain rule.

62
Training Chain Rule
Given:
Chain Rule:
…

Backpropagation:
1. Instantiate the computation as a directed acyclic graph, where each
intermediate quantity is a node
2. At each node, store (a) the quantity computed in the forward pass
and (b) the partial derivative of the goal with respect to that node’s
intermediate quantity.
3. Initialize all partial derivatives to 0.
4. Visit each node in reverse topological order. At each node, add its
contribution to the partial derivatives of its parents

This algorithm is also called automatic differentiation in the reverse-

mode 63
Training Backpropagation

64
Training Backpropagation

65
Training Backpropagation
Output

Case 1:
Logistic θ1 θ2 θ3 θM
Regression
…
Input

66
Training Backpropagation

Output

…
Hidden Layer

…
Input

67
Training Backpropagation

Output

…
Hidden Layer

…
Input

68
Training Backpropagation
Case 2:
Neural
Network

69
Training Chain Rule
Given:
Chain Rule:
…

Backpropagation:
1. Instantiate the computation as a directed acyclic graph, where each
intermediate quantity is a node
2. At each node, store (a) the quantity computed in the forward pass
and (b) the partial derivative of the goal with respect to that node’s
intermediate quantity.
3. Initialize all partial derivatives to 0.
4. Visit each node in reverse topological order. At each node, add its
contribution to the partial derivatives of its parents

This algorithm is also called automatic differentiation in the reverse-

mode 70
Training Chain Rule
Given:
Chain Rule:
…

Backpropagation:
1. Instantiate the computation as a directed acyclic graph, where each
node represents a Tensor.
2. At each node, store (a) the quantity computed in the forward pass
and (b) the partial derivatives of the goal with respect to that node’s
Tensor.
3. Initialize all partial derivatives to 0.
4. Visit each node in reverse topological order. At each node, add its
contribution to the partial derivatives of its parents

This algorithm is also called automatic differentiation in the reverse-

mode 71
Training Backpropagation
Case 2:
Neural
Module 5
Network

Module 4
…

Module 3

Module 2

Module 1

72
 A Recipe for
Background
Gradients
Machine Learning
1. Given training data: 3. Definecan
Backpropagation goal:
compute this
gradient!
And it’s a special case of a more
general algorithm called reverse-
2. Choose each of these:mode automatic differentiation that
– Decision function can compute
4. Train
the with SGD:
gradient of any
differentiable
(takefunction efficiently!
small steps
opposite the gradient)
– Loss function

73
 Lib and Framework for deep
learning
• Many deep learning library and frameworks have been
developed (special, 2017):
– Tensorflow (Google)
– PyTorch (Facebook)
– Theano* (LISA lab, university of montreal)
– MXNet (Amazon)
– CNTK (Microsoft)
– Caffe
– Deeplearning4j
– …

74
 Summary
1. Neural Networks…
– provide a way of learning features
– are highly nonlinear prediction functions
– (can be) a highly parallel network of logistic regression classifiers
– discover useful hidden representations of the input
2. Backpropagation…
– provides an efficient way to compute gradients
– is a special case of reverse-mode automatic differentiation

75
 Demo
• http://playground.tensorflow.org

76
 Reference
• Lecture slides - Introduction Machine Learning, CMU, 2016.
• Introduction to Deep Learing, MIT, 2017

77