Learning Algorithm and Neural Networks

74
Learning Algorithm and Neural Networks Dr. Alaa Sagheer [email protected] MTR607- Spring 2012 Egypt-Japan University

description

Dr. Alaa Sagheer [email protected]. Learning Algorithm and Neural Networks. MTR607- Spring 2012 Egypt-Japan University. MTR 607. Textbook: Simon Haykin, “Neural Networks A Comprehensive Foundation,” 2 nd Ed., 1999 Lecturer: Dr. Alaa Sagheer - PowerPoint PPT Presentation

Transcript of Learning Algorithm and Neural Networks

Page 1: Learning Algorithm and Neural Networks

Learning Algorithm and Neural Networks

Dr. Alaa [email protected]

MTR607- Spring 2012Egypt-Japan University

Page 2: Learning Algorithm and Neural Networks

MTR 607

Textbook: Simon Haykin, “Neural Networks A Comprehensive

Foundation,” 2nd Ed., 1999

Lecturer: Dr. Alaa Sagheer

Place: Seminar Room, E-JUST

Grading: Class participation (10%),

Assignments and reports (20%),

Midterm test (30%),

Final exam (40%)

2MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 3: Learning Algorithm and Neural Networks

Course Overview Introduction to Artificial Neural Networks, Artificial and human neurons (Biological Inspiration) The learning process, Supervised and unsupervised learning, Reinforcement learning, Applications Development and Portfolio The McCulloch-Pitts Model of Neuron, A simple network layers, Multilayer networks Perceptron, Back propagation algorithm, Recurrent networks, Associative memory, Self Organizing maps, Support Vector Machine and PCA, Applications to speech, vision and control problems.

Introduction to Artificial Neural Networks, Artificial and human neurons (Biological Inspiration) The learning process, Supervised and unsupervised learning, Reinforcement learning, Applications Development and Portfolio The McCulloch-Pitts Model of Neuron, A simple network layers, Multilayer networks Perceptron, Back propagation algorithm, Recurrent networks, Associative memory, Self Organizing maps, Support Vector Machine and PCA, Applications to speech, vision and control problems.

3MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 4: Learning Algorithm and Neural Networks

ANN’s ResourcesMain text books:“Neural Networks: A Comprehensive Foundation”, S. Haykin (very good -theoretical)“Pattern Recognition with Neural Networks”, C. Bishop (very good-more accessible)“Neural Network Design” by Hagan, Demuth and Beale (introductory)

Books emphasizing the practical aspects:“Neural Smithing”, Reeds and Marks “Practical Neural Network Recipees in C++”’ T. Masters

Seminal Paper:“Parallel Distributed Processing” Rumelhart and McClelland et al.

Other:“Neural and Adaptive Systems”, J. Principe, N. Euliano, C. Lefebvre

4MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 5: Learning Algorithm and Neural Networks

Review Articles: R. P. Lippman, “An introduction to Computing with Neural Nets”’ IEEE ASP Magazine, 4-22, April 1987.

T. Kohonen, “An Introduction to Neural Computing”, Neural Networks, 1, 3-16, 1988.

A. K. Jain, J. Mao, K. Mohuiddin, “Artificial Neural Networks: A Tutorial”’ IEEE Computer, March 1996’ p. 31-44.

ANN’s Resources

5MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 6: Learning Algorithm and Neural Networks

Course Overview Introduction to Artificial Neural Networks, Artificial and human neurons (Biological Inspiration) The learning process,

Supervised and unsupervised learning, Reinforcement learning, Applications Development and Portfolio The McCulloch-Pitts Model of Neuron, A simple network layers, Multilayer networks Perceptron, Back propagation algorithm, Recurrent networks, Associative memory, Self Organizing maps, Support Vector Machine and PCA, Applications to speech, vision and control problems.

Introduction to Artificial Neural Networks, Artificial and human neurons (Biological Inspiration) The learning process,

Supervised and unsupervised learning, Reinforcement learning, Applications Development and Portfolio The McCulloch-Pitts Model of Neuron, A simple network layers, Multilayer networks Perceptron, Back propagation algorithm, Recurrent networks, Associative memory, Self Organizing maps, Support Vector Machine and PCA, Applications to speech, vision and control problems.

6MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 7: Learning Algorithm and Neural Networks

Part I:

1. Artificial Neural Networks

2. Artificial and human neurons (Biological Inspiration)

3. Tasks & Applications of ANNs

Part II:

1. Learning in Biological Systems

2. Learning with Artificial Neural Networks

Introduction to Artificial Neural Networks

7MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 8: Learning Algorithm and Neural Networks

ANNs vs. ComputersDigital Computers

• Analyze the problem to be solved

• Deductive Reasoning. We apply known rules to input data to produce output.

• Computation is centralized, synchronous, and serial.

• Not fault tolerant. One transistor goes and it no longer works.

• Static connectivity.

• Applicable if well defined rules with precise input data.

8MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Artificial Neural Networks No requirements of an explicit

description of the problem.• Inductive Reasoning. Given input and

output data (training examples), we construct the rules.

• Computation is collective, asynchronous, and parallel.

• Fault tolerant and sharing of responsibilities.

• Dynamic connectivity.

• Applicable if rules are unknown or complicated, or if data are noisy or partial.

Page 9: Learning Algorithm and Neural Networks

What is ANN?

9MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

ANN is a branch of "Artificial Intelligence". It is a system modeled based on the human brain. ANN goes by many names, such as connectionism, parallel distributed processing, neuro-computing, machine learning algorithms, and finally, artificial neural networks.

Developing ANNs date back to the early 1940s. It experienced a wide popularity in the late 1980s. This was a result of the discovery of new techniques and developments in PCs.

Some ANNs are models of biological neural networks and some are not.

ANN is a processing device (An algorithm or Actual hardware) whose design was motivated by the design and functioning of human brain.

Inside ANN:

ANN’s design is what distinguishes neural networks from other mathematical techniquesANN is a network of many simple processors ("units“ or “neurons”), each unit has a small amount of local memory. The units are connected by unidirectional communication channels ("connections"), which carry numeric (as opposed to symbolic) data. The units operate only on their local data and on the inputs they receive via the connections.

Artificial Neural Networks (1)

Page 10: Learning Algorithm and Neural Networks

ANNs Operation

ANNs normally have great potential for parallelism (multiprocessor-friendly architecture), since the computations of the units are independent of each other. Same like biological neural networks. Most neural networks have some kind of "training" rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, neural networks "learn" from examples, just like children…and exhibit some structural capability for generalization.

10MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Artificial Neural Networks (2)

Page 11: Learning Algorithm and Neural Networks

ANNs are a powerful technique (Black Box) to solve many real world problems. They have the ability to learn from experience in order to improve their performance and to adapt themselves to changes in the environment.

In addition, they are able to deal with incomplete information or noisy data and can be very effective especially in situations where it is not possible to define the rules or steps that lead to the solution of a problem.

Once trained, the ANN is able to recognize similarities when presented with a new input pattern, resulting in a predicted output pattern.

11MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Artificial Neural Networks (3)

Page 12: Learning Algorithm and Neural Networks

What can a ANN do?

Compute a known functionApproximate an unknown functionPattern RecognitionSignal Processing

…………..Learn to do any of the above

Page 13: Learning Algorithm and Neural Networks

Part I:

1. Artificial Neural Networks (ANNs)

2. Artificial and human neurons (Biological Inspiration)

3. Tasks & Applications of ANNs

Part II:

1. Learning in Biological Systems

2. Learning with Artificial Neural Networks

Introduction to Artificial Neural Networks

13MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 14: Learning Algorithm and Neural Networks

Biological Inspiration

Animals are able to react adaptively to changes in their external and internal environment, and they use their nervous system to perform these behaviours.

An appropriate model/simulation of the nervous system should be able to produce similar responses and behaviours in artificial systems.

The nervous system is build by relatively simple units, the neurons, so copying their behaviour and functionality should be the solution!

Biological Neural Networks (BNN) are much more complicated in their elementary structures than the

mathematical models we use for ANNs

14MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 15: Learning Algorithm and Neural Networks

ANN as a model of brain-like Computer

BrainThe human brain is still not well understood and indeed its behavior is very complex!There are about 10-11 billion neurons in the human cortex each connected to , on average, 10000 others. In total 60 trillion synapses of connections.The brain is a highly complex, nonlinear and parallel computer (information-processing system)

ANN as a Brain-Like Computer

15MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

An artificial neural network (ANN) is a massively parallel distributed processor that has a natural propensity for storing experimental knowledge and making it

available for use. It means that: 

Knowledge is acquired by the network through a learning (training) process; The strength of the interconnections between neurons is implemented by means of the synaptic weights used to store the knowledge.

The learning process is a procedure of the adapting the weights with a learning

algorithm in order to capture the knowledge. On more mathematically, the aim of the

learning process is to map a given relation between inputs and output of the network.

Page 16: Learning Algorithm and Neural Networks

Massive parallelism Brain computer as an information or signal processing system, is composed of a large number of a simple processing elements, called neurons. These neurons are interconnected by numerous direct links, which are called connection, and cooperate which other to perform a parallel distributed processing (PDP) in order to soft a desired computation tasks.

Connectionism Brain computer is a highly

interconnected neurons system in such a way that the state of one

neuron affects the potential of the large number of other neurons

which are connected according to weights or strength. The key idea of such principle is the functional capacity of biological neural nets deters mostly not so of a single neuron but of its connections 

Associative distributed memoryStorage of information in a brain is supposed to be concentrated in synaptic connections of brain neural network, or more precisely, in the pattern of these connections and strengths (weights) of the synaptic connections.

A process of pattern recognition and pattern

manipulation is based on:

How our brain manipulates 

with patterns ?

Principles of Brain Processing

16MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 17: Learning Algorithm and Neural Networks

17MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Biological Neuron

- The simple “arithmetic computing”

element

Biological Neuron

Page 18: Learning Algorithm and Neural Networks

Cell structuresCell body

Dendrites

Axon

Synaptic terminals

Biological Neuron (2)

18MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 19: Learning Algorithm and Neural Networks

synapses

axon dendrites

The information transmission happens at the synapses, i.e

Synaptic connection strengths among neurons are used to store the acquired knowledge.

In a biological system, learning involves adjustments to the synaptic connections between neurons

19MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Biological Neurons (3)

Page 20: Learning Algorithm and Neural Networks

Biological Neurons (4)

20MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

1. Soma or body cell - is  a  large,  round central  body  in  which  almost  all  the logical  functions  of  the  neuron  are realized (i.e. the processing unit).

2. The axon (output), is  a  nerve  fibre attached to  the soma which can serve as  a  final  output  channel  of  the neuron.  An  axon  is  usually  highly branched.

3. The dendrites (inputs)-  represent  a highly  branching  tree  of  fibers.  These long  irregularly  shaped  nerve  fibers (processes)  are attached  to  the  soma  carrying electrical signals to the cell 

4. Synapses  are  the  point  of  contact between  the axon of one cell  and  the dendrite  of  another,  regulating    a chemical  connection  whose  strength affects the input to the cell.

The schematic model of a

biological neuron

Synapses

Dendrites

Soma

AxonDendrite

from other

Axon from other

neuron

Page 21: Learning Algorithm and Neural Networks

Properties of ANNsLearning from examples

labeled or unlabeled

Adaptivity

changing the connection strengths to learn things

Non-linearity

the non-linear activation functions are essential

Fault tolerance

if one of the neurons or connections is damaged, the whole network still works quite well

Page 22: Learning Algorithm and Neural Networks

Part I:

1. Artificial Neural Networks (ANNs)

2. Artificial and human neurons (Biological Inspiration)

3. Tasks & Applications of ANNs

Part II:

1. Learning in Biological Systems

2. Learning with Artificial Neural Networks

Introduction to Artificial Neural Networks

22MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 23: Learning Algorithm and Neural Networks

Applications of ANNsClassification

In marketing: consumer spending pattern classification

In defence: radar and sonar image classification

In agriculture & fishing: fruit, fish and catch grading

In medicine: ultrasound and electrocardiogram image classification, EEGs, medical diagnosis

Recognition and Identification

In general computing and telecommunications: speech, vision and handwriting recognition

In finance: signature verification and bank note verification

Assessment

In engineering: product inspection monitoring and control

In defence: target tracking

In security: motion detection, surveillance image analysis and fingerprint matching

Forecasting and Prediction

In finance: foreign exchange rate and stock market forecasting

In agriculture: crop yield forecasting , Deciding the category of potential food items

(e.g., edible or non-edible)

In marketing: sales forecasting

In meteorology: weather prediction

MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer23

Page 24: Learning Algorithm and Neural Networks

Who are the Men of ANNs?! Computer scientists want to find out about the properties of non-symbolic information processing with neural nets and about learning systems in general. Statisticians use neural nets as flexible, nonlinear regression and classification models. Engineers of many kinds exploit the capabilities of neural networks in many areas, such as signal processing and automatic control. Cognitive scientists view neural networks as a possible apparatus to describe models of thinking and consciousness (High-level brain function). Neuro-physiologists use neural networks to describe and explore medium-level brain function (e.g. memory, sensory system, motorics). Physicists use neural networks to model phenomena in statistical mechanics and for a lot of other tasks. Biologists use Neural Networks to interpret nucleotide sequences. Philosophers and some other people may also be interested in Neural Networks for various reasons

24MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 25: Learning Algorithm and Neural Networks

Operation of Biological Neuron The spikes travelling along the axon of the pre-synaptic neuron trigger the release of neurotransmitter substances at the synapse.The neurotransmitters cause excitation or inhibition in the dendrite of the post-synaptic neuron.The integration of the excitatory and inhibitory signals may produce spikes in the post-synaptic neuron. The contribution of the signals depends on the strength of the synaptic connection.

25MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

• Excitation means positive product between the incoming spike rate and the corresponding synaptic weight;

• Inhibition means negative product between the incoming spike rate and the corresponding synaptic weight;

Page 26: Learning Algorithm and Neural Networks

Inputs

Output

An artificial neural network is composed of many artificial neurons that are linked together according to a specific network architecture. The objective of the neural network is to transform the inputs into

meaningful outputs.

ANN Architecture

26MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 27: Learning Algorithm and Neural Networks

Neurons are arranged in layers. Neurons work by processing information. They receive and provide information in form of spikes.

27MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

The artificial neuron receives one or more inputs (representing the one or more dendrites),

At each neuron, every input has an associated weight which modifies the strength of each input and sums them together,

The sum of each neuron is passed through a function known as an activation function or transfer function in order to produce an output (representing a biological neuron's axon)

ANN Architecture (2)

Inputs Output

Page 28: Learning Algorithm and Neural Networks

Inputs

Outputw2

w1

w3

wn

wn-1

. . .

x1

x2

x3

xn-1

xn

y)(;

1

zHyxwzn

iii

Each neuron takes one or more inputs and produces an output. At each neuron, every input has an associated weight which modifies the strength of each input. The neuron simply adds together all the inputs and calculates an output to be passed on.

28MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

ANN Architecture (3)

Page 29: Learning Algorithm and Neural Networks

Models of A Neuron

29MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 30: Learning Algorithm and Neural Networks

Axon

Terminal Branches of Axon

Dendrites

S

x1

x2

w1

w2

wnxn

x3 w3

Models of A Neuron (2)

30MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 31: Learning Algorithm and Neural Networks

1. A set of synapses, or connection link: each of which is characterized by a weight or strength of its own wkj. Specifically, a signal xj at the input synapse ‘j’ connected to neuron ‘k’ is multiplied by the synaptic wkj

2. An adder: For summing the input signals, weighted by respective synaptic strengths of the neuron in a linear operation.

3. Activation function: For limiting of the amplitude of the output of the neuron to limited range. The activation function is referred to as a Squashing (i.e. limiting) function {interval [0,1], or, alternatively [-1,1]}

Models of A Neuron (3)

Three elements:

31MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 32: Learning Algorithm and Neural Networks

BiasThe bias has the effect of increasing or lowering the net input of the activation function depending on whether it is +/-

yk = Ø(vk) = Ø(uk + bk) = Ø(Swkjxj + bk)An artificial neuron:

-computes the weighted sum of its input (called its net input)

-adds its bias (the effect of applying affine transformation to the output vk)

-passes this value through an activation function

We say that the neuron “fires” (i.e. becomes active) if its outputs is above zero.

This extra free variable (bias) makes the neuron more powerful.

32MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 33: Learning Algorithm and Neural Networks

Activation Function Ø(vk)It defines the output of the neuron given an input or set of inputs. A standard computer chip circuit can be seen as a digital network of activation functions that can be "ON" (1) or "OFF" (0), depending on input,

The best activation function is the non-linear function. Linear functions are limited because the output is simply proportional to the input.

33MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Three basic types of activation function:

1. Threshold function,

2. Linear function,

3. Sigmoid function.

Page 34: Learning Algorithm and Neural Networks

Threshold (Step) function

The output yk of this activation function is binary, depending on whether the input meets a specified threshold. The "signal" is sent, i.e. the output is set to one, if the activation meets the threshold.

Activation functions (2)

McColloch-Pitts ModelThreshold Logic Unit

(TLU), since 1943

34MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 35: Learning Algorithm and Neural Networks

Piecewise Linear Function- The amplification factor inside the linear region of operation is assumed to be unity. - This form may be viewed as an approximation to a non linear amplifier

Activation functions (3)

35MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 36: Learning Algorithm and Neural Networks

Sigmoid function

Where “a” is the slope parameter of

the sigmoid function

Activation functions (4)

- A fairly simple non-linear function, such as the logistic function.

- As the slop parameter approaches infinity the sigmoid function becomes a threshold function

36MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 37: Learning Algorithm and Neural Networks

Artificial Neural Networks

Early ANN Models:McCulloch-Pitts , Perceptron, ADALINE, Hopfield Network,

Current Models:Multilayer feed forward networks (Multilayer perceptrons- Back propagation )

Radial Basis Function networks

Self Organizing Networks

...

37MTR607: Learning Algorithms and Neural Networks Dr. Alaa Sagheer

Page 38: Learning Algorithm and Neural Networks

FeedbackFeedback is a dynamic system whenever occurs in almost every part of the nervous system,

Feedback is giving one or more closed path for transmission of signals around the system,

It plays important role in study of special class of neural networks known as Recurrent networks.

Page 39: Learning Algorithm and Neural Networks

Feedback (2)

The system is assumed to be linear and has a forward path (A) and a feedback path (B),

The output of the forward channel determines its own output through the feedback channel.

Page 40: Learning Algorithm and Neural Networks

Feedback (3)

E.g. consider A is a fixed weight and B is a unit delay operator z-1 .

Page 41: Learning Algorithm and Neural Networks

Feedback (4)

Then, we may express yk(n) as an infinite weighted summation of present and past samples of the input signal xj(n).

Therefore, feedback systems are controlled by weight.

Page 42: Learning Algorithm and Neural Networks

Feedback (5)

Feedback systems are controlled by weight.

1. For positive weight, we have stable systems, i,e, convergent output y,

2. For negative weight, we have, unstable systems, i.e divergent output y.. (Linear and Exponential)

Page 43: Learning Algorithm and Neural Networks

Network Architectures

Three different classes of network architectures:

1. Single-layer feed forward networks,

2. Multilayer feed forward networks,

3. Recurrent networks.

Page 44: Learning Algorithm and Neural Networks

Single-layer feed forward network

- Input layer of source nodes that projects directly

onto an output layer of neurons.

- “Single-layer” referring to the output layer of computation nodes (neuron).

Page 45: Learning Algorithm and Neural Networks

Multilayer feed forward network

It contains one or more hidden layers (hidden neurons).

“Hidden” refers to the part of the neural network is not seen directly from either input or output of the network .

The function of hidden neuron is to intervene between input and output.

By adding one or more hidden layers, the network is able to extract higher-order statistics from input

Page 46: Learning Algorithm and Neural Networks

Recurrent NetworksIt is different from feed forward neural network in that it has at least one feedback loop.

Recurrent network may consist of single layer of neuron with each neuron feeding its output signal back to the inputs of all the other neurons. Note: There are no self-feedback.

Feedback loops have a profound impact on learning and overall performance.

Page 47: Learning Algorithm and Neural Networks

Slide 47

What transfer function should be used?

How many inputs does the network need?

How many hidden layers does the network need?

How many hidden neurons per hidden layer?

How many outputs should the network have?

There is no standard methodology to determinate these values. Even there is some heuristic points, final values are

determinate by a trial and error procedure.

How to Decide on a Network Topology?

Page 48: Learning Algorithm and Neural Networks

Knowledge Representation

The main characteristic of knowledge representation has two folds:1) What information is actually made explicit?2) How the information is physically encoded for subsequent use?

KnowledgeKnowledge is referred to the stored information or models used by a person or machine to interpret, predict and, appropriately, respond to the outside.

A good solution depends on a good representation of knowledge

Page 49: Learning Algorithm and Neural Networks

There are two kinds of Knowledge: 1) The known world states, or facts, (prior knowledge), 2) Observations (measurements) of the world, obtained by sensors to probe the environment.

Knowledge Representation (2)

These observations represent the pool of information, from which examples are used to train the NN

Page 50: Learning Algorithm and Neural Networks

These Examples can be labeled or unlabeled

In labeled examples Each example representing an input signal is paired with a corresponding desired response,Labeled examples may be expensive to collect, as they require availability of a “teacher” to provide a desired response for each labeled example.

Un labeled examplesUnlabeled examples are usually abundant as there is no need for supervision.

Knowledge Representation (3)

Page 51: Learning Algorithm and Neural Networks

Design of neural network may proceed as follow:

An appropriate architecture for the neural network, with an input layer consisting of source nodes equal in number to the pixels of an input image.

The recognition performance of trained network is tested with data not seen before (testing).

This phase of the network design called learning

Knowledge Representation (3)

Page 52: Learning Algorithm and Neural Networks

Roles of Knowledge RepresentationThere are four rules for knowledge representation:

Rule 1:Rule 1:

Similar inputs (i.e., patterns) drawn from similar classes should usually produce similar representation inside the network, and should therefore be classified as belonging to the same class.

There are plethora (many) of measures for determining the similarity between inputs

Page 53: Learning Algorithm and Neural Networks

(1)

Roles of Knowledge Representation (2)A commonly used measure of similarity is the Euclidian DistanceEuclidian Distance

Let xi denotes an m-by-1 vector

Page 54: Learning Algorithm and Neural Networks

Roles of Knowledge Representation (3)Another measure is the dot product dot product or inner product inner product com

Given a pair of vectors xi and xj of the same dimension, their inner product will be (the projection of vector xi onto vector xj)

Please note that:

Page 55: Learning Algorithm and Neural Networks

Using Eq.(1) to write

Roles of Knowledge Representation (4)

The smaller the Euclidean distance ║x i - xj ║(i.e. the more

similar the vector xi and xj are), the larger the inner product xiT

xj will be.To formalize this relationship, we normalize the vectors x i

and xj to have a unit length, i.e.:

The minimization of the Euclidean distance d(x i , xj )

corresponds to maximization of the inner product (x i , xj )..and,

therefore, the similarity between the vectors x i and xj

Page 56: Learning Algorithm and Neural Networks

If the vectors x i and xj are stochastic (drown from different

population of data)

Roles of Knowledge Representation (5)

Where C-1 is the inverse of the covariance matrix C. It is supposed that the covariance matrix is the same for both

For a prescribed C, the smaller the distance d is the more similar the vectors xi and xj will be

Page 57: Learning Algorithm and Neural Networks

Rule 2:Rule 2:Item to be categorized as separate classes should be given widely different representation in work.

Rule 3: Rule 3: If a particular feature is important, then there should be large number of neurons involved in the representation of that item in the network.

Rule 4: Rule 4: Prior information and invariance should be built into the design of a neural network when ever they are available, so as to simplify the network design by its not having to learn them.

Roles of Knowledge Representation (6)

Rule 4 is particularly important and highly desirable

Page 58: Learning Algorithm and Neural Networks

1) Biological visual and auditory networks are very specialized,

2) NN with SS has a smaller number of free parameters available for

adjustment than other networks. Then, they need a small training dataset,

learns faster and generalize better.

3) Rate of information transmission through a specialized network is faster,

4) Cost of building a specialized network is minimum, due to small size.

Roles of Knowledge Representation (7)

Rule 4 is particularly important and highly desirable because it results in an NN with a Specialized Structure (SS)

Page 59: Learning Algorithm and Neural Networks

How to build prior information into NN design?

There are currently no well-defined rules for doing this; but we have some procedure are known to yield useful rules. In particular, we may use a combination of two techniques: 1. Restricting the network architecture (using local connections)2. Constraining the choice of synaptic weight (using the weight sharing)

The latter tech is so important because it

leads to reducing significantly free

parameters

Page 60: Learning Algorithm and Neural Networks

How to build invariance into NN’s design?

There are three technique for rendering classifier-type NNs invariant to transformations: 1. Invariance by structure.2. Invariance by training.3. Invariance by feature space

Consider any of the following:1) When an object rotates, the perceived image, by observer, will change as

well,2) The utterance of a spoken person may be soft or loud..slower or quicker,3) …..

A classifier should be invariant to different transformationOr

A class estimate represented by an output of the classifier MUST not be affected by transformations of the observed

signal applied to the classifier input

Page 61: Learning Algorithm and Neural Networks

Learning in Biological Systems

Page 62: Learning Algorithm and Neural Networks

Learning in Biological SystemsLearning approach based on modeling adaptation in biological neural systems

Learning = learning by adaptation

The young animal learns that the green fruits are sour, while the yellowish/reddish ones are sweet. The learning happens by adapting the fruit picking behaviour

Page 63: Learning Algorithm and Neural Networks

From experience: examples / training data

Learning happens by changing of the synaptic strengths,

Synapses change size and strength with experience (or examples or training data),

Strength of connection between the neurons is stored as a weight-value for the specific connection,

Learning the solution to a problem = changing the connection weights

Learning in Biological Systems (2)

Page 64: Learning Algorithm and Neural Networks

Hebbian Learning

When two connected neurons are firing at the same time, the strength of the synapse between them increases,

“Neurons that fire together, wire together”

Learning in Biological Systems (3)

Page 65: Learning Algorithm and Neural Networks

Learning in ANN

We may categorize the learning process through Neural Networks function as follows:

1. Learning with a teacher, - Supervised Learning

2. Learning without a teacher, - Unsupervised Learning

- Reinforcement Learning

Page 66: Learning Algorithm and Neural Networks

In supervised learning, both the inputs and the outputs are provided. The network then processes the inputs and compares its resulting outputs against the desired outputsErrors are then calculated, causing the system to adjust the weights which control the network. This process occurs over and over as the weights are continually improved.

Supervised Learning

Supervised learning process constitutes a closed-loop feedback system but unknown environment is outside the loop,

Page 67: Learning Algorithm and Neural Networks

It is based on a labeled training set.

The class of each piece of data in training set is known.

Class labels are pre-determined and provided in the training phase.

A

BA

BA

B

Class

Class

Class

Class

Class

Class

Supervised Learning (2)

Page 68: Learning Algorithm and Neural Networks

Understanding Supervised Learning

A

BA

B A

B

Page 69: Learning Algorithm and Neural Networks

Two Possible Solutions…

A

B

A

B

A

B

A

B A

B

A

B

Page 70: Learning Algorithm and Neural Networks

How to solve a given problem of supervised learning?

Various steps have to be considered:

1. Determine the type of training examples,

2. Gather a training data set that satisfactory describe the given problem,

3. After the training process we can test the performance of learned artificial

neural network with the test (validation) data set,

4. Test data set consist of data that has not been introduced to artificial

neural network while learning.

Page 71: Learning Algorithm and Neural Networks

Reinforcement Learning

The learning of input –output mapping is performed through continued interaction with the environment in order to minimize a scalar index of performance.

Or A machine learning technique that sets parameters of an artificial neural network, where data is usually not given, but generated by interactions with the environment.

Page 72: Learning Algorithm and Neural Networks

Reinforcement Learning (2)

Reinforcement learning is built around critic that converts primary reinforcement signal received from the environment into a higher

quality reinforcement signal

Page 73: Learning Algorithm and Neural Networks

Unsupervised LearningNo help from the outside,

No information available on the desired output,Input: set of patterns P, from n-dimensional space S, but little / no information about their classification, evaluation, interesting features, etc.

It must learn these by itself! Learning by doing

Tasks: Used to pick out structure in the inputClustering - Group patterns based on similarity,Vector Quantization - Fully divide up S into a small set of regions (defined by codebook vectors) that also helps cluster P,Feature Extraction - Reduce dimensionality of S by removing unimportant features (i.e. those that do not help in clustering P)

Page 74: Learning Algorithm and Neural Networks

Supervised vs. Unsupervised

Task performedClassificationPattern Recognition

• NN model Preceptron,Feed-Forward NN

Task performedClustering, Pattern Recognition

Feature Extraction, VQ

• NN Model Self Organizing Maps,

ART