2. 2
CONTENTS:
INTRODUCTION TO NEURAL NETWORKS
WHAT ARE NEURAL NETWORKS?
BASIC STRUCTURE
TYPES OF ANN
WORKING
APPLICATIONS
ADVANTAGES AND DISADVANTAGES
CONCLUSION
3. 3
“ARTIFICAL NEURAL NETWORKS”
Introduction to Neural Networks
Neural networksare a popular target representation forlearning. These networks are inspired by
the neurons in the brain but do not actually simulate neurons. Artificialneural networks typically
contain many fewer than the approximately 10 neurons that are in the human brain, and the
artificial neurons, called units,are much simpler than their biologicalcounterparts.
Artificial neural networksare interesting to study fora number of reasons:
As part of neuroscience, to understand real neural systems, researchers are simulating the
neural systems of simple animals such as worms, which promise to lead to an
understanding about which aspects of neural systems are necessary to explain the behavior
of these animals.
Some researchers seek to automate not only the functionality of intelligence (whichis what
the field of artificial intelligence is about) but also the mechanism of the brain, suitably
abstracted. One hypothesis is that the only way to build the functionality of the brain is by
using the mechanism of the brain. This hypothesis can be tested by attempting to build
intelligence using the mechanism of the brain, as well as without using the mechanism of
the brain. Experience with building other machines - such as flying machines, whichuse the
same principles, but not the same mechanism that birds use to fly - would indicate that this
hypothesis may not be true. However,it is interesting to test the hypothesis.
The brain inspires a new way to think about computation that contrasts withcurrently
available computers. Unlike current computers, which have a few processors and a large but
essentially inert memory, the brain consists of a huge number of asynchronous distributed
processes, all running concurrently withno master controller.One should not think that the
current computers are the only architecture available forcomputation.
As far as learning is concerned, neural networks provide a different measure of simplicity as
a learning bias than, for example, decision trees. Multilayer neural networks, like decision
trees, can represent any function of a set of discrete features. However,the functionsthat
correspond to simple neural networks do not necessarily correspond to simple decision
trees. Neural networklearning imposes a different bias than decision tree learning. Whichis
better, in practice, is an empirical question that can be tested on differentdomains?
4. 4
What are Artificial Neural Networks (ANNs)?
The inventor of the first neurocomputer, Dr. Robert Hecht-Nielsen, defines a neural networkas −
"...a computing system made up of a number of simple, highly interconnected processing elements,
whichprocess information by their dynamic state response to external inputs.”OR
An artificialneuron network(ANN) is a computational model based on the structure and functions
of biological neural networks. Information that flowsthrough the network affectsthe structure of
the ANN because a neural networkchanges - or learns, in a sense - based on that input and output.
Basic Structureof ANNs
The idea of ANNs is based on the belief that working of human brain by making the right
connections can be imitated using silicon and wires as living neurons and dendrites.
The human brain is composed of 86 billion nerve cells called neurons.They are connectedto other
thousand cells by Axons.Stimuli fromexternal environment or inputs from sensory organs are
accepted by dendrites. These inputs create electric impulses, whichquickly travel through the
neural network.A neuron can then send the message to other neuron to handle the issue or does
not send it forward.
5. 5
ANNs are composed of multiple nodes,whichimitate biological neuronsof human brain. The
neurons are connectedby links and they interact with each other. The nodes can take input data
and perform simple operations on the data. The result of these operations is passed to other
neurons. The output at each node is called its activationor nodevalue.
Eachlink is associated with weight.ANNs are capable of learning, whichtakes place by altering
weight values. The followingillustration shows a simple ANN.
Types of Artificial Neural Networks
There are twoArtificial Neural Networktopologies − Feed Forwardand Feedback.
6. 6
Feed Forward ANN
The information flow is unidirectional. A unit sends information to other unit from whichit does
not receive any information. There are no feedback loops. They are used in pattern
generation/recognition/classification. They have fixed inputs and outputs.
Feedback ANN
Here, feedbackloops are allowed. They are used in contentaddressable memories.
7. 7
Working of ANNs
In the topology diagrams shown, each arrow represents a connectionbetween two neurons and
indicates the pathway forthe flow of information. Each connectionhas a weight, an integer number
that controls the signal between the twoneurons.
If the networkgenerates a “good or desired” output, there is no need to adjust the weights.
However,if the network generates a “pooror undesired” output or an error, then the system alters
the weights in order to improve subsequent results.
Machine Learning in ANNs
ANNs are capable of learning and they need to be trained. There are several learning strategies −
SupervisedLearning −It involvesa teacher that is scholar than the ANN itself. For
example, the teacher feeds some example data about which the teacher already knowsthe
answers.
For example, pattern recognizing. The ANN comes up withguesses while recognizing. Then the
teacher provides the ANN with the answers. The networkthen compares it guesses with the
teacher’s “correct” answers and makes adjustments according to errors.
UnsupervisedLearning −It is required when there is no example data set with known
answers. For example, searching fora hidden pattern. In this case, clustering i.e. dividing a
set of elements into groups accordingto some unknown pattern is carried out based on the
existing data sets present.
ReinforcementLearning −this strategy built on observation. The ANN makes a decision
by observing its environment. If the observation is negative, the network adjusts its weights
to be able to make a different required decision the next time.
Back PropagationAlgorithm
8. 8
It is the training or learning algorithm. It learns by example. If yousubmit to the algorithm the
example of whatyou want the network to do, it changes the network’s weights so that it can
produce desired output fora particular input on finishing the training.
Back Propagation networksare ideal forsimple Pattern Recognition and Mapping Tasks.
BayesianNetworks(BN)
These are the graphical structures used to represent the probabilistic relationship among a set of
random variables. Bayesian networks are also called BeliefNetworks orBaysNets. BNs reason
about uncertain domain.
In these networks, each node represents a random variable withspecific propositions. For example,
in a medical diagnosis domain, the node Cancer represents the proposition that a patient has
cancer.
The edges connecting the nodes represent probabilistic dependencies among those random
variables. If out of twonodes, one is affectingthe other then they must be directly connected in the
directions of the effect.The strength of the relationship between variables is quantified by the
probability associated witheach node.
There is an only constraint on the arcs in a BN that you cannot return to a node simply by following
directed arcs. Hence the BNs are called Directed Acyclic Graphs (DAGs).
BNs are capable of handling multivalve variables simultaneously. The BN variables are composed of
twodimensions −
Range of prepositions
Probability assigned to each of the prepositions.
Consider a finite set X = {X1, X2, …,An} of discrete random variables, where each variable Xi may take
values from a finite set, denoted by Val(Xi).If there is a directed link from variable Xi to variable, Xj,
then variable Xi willbe a parent of variable Ax showing direct dependencies between the variables.
The structure of BN is ideal forcombining prior knowledge and observed data. BN can be used to
learn the causal relationships and understand various problem domains and to predict future
events, even in case of missing data.
Applications of Neural Networks:
They can perform tasks that are easy fora human but difficultfora machine −
Aerospace− Autopilot aircrafts, aircraft fault detection.
Automotive− Automobile guidance systems.
9. 9
Military− Weapon orientation and steering, target tracking, objectdiscrimination, facial
recognition, signal/image identification.
Electronics− Code sequence prediction, IC chip layout,chip failure analysis, machine vision,
voicesynthesis.
Financial − Real estate appraisal, loan advisor, mortgage screening, corporate bond rating,
portfoliotrading program, corporate financial analysis, currency value prediction, document
readers, credit application evaluators.
Industrial − Manufacturing process control, productdesign and analysis, quality inspection
systems, welding quality analysis, paper quality prediction, chemical product design analysis,
dynamic modeling of chemical process systems, machine maintenance analysis, project bidding,
planning, and management.
Medical −Cancer cell analysis, EEGand ECG analysis, prosthetic design, transplant time
optimizer.
Speech− Speech recognition, speech classification, text to speech conversion.
Telecommunications−Image and data compression, automated information services,
real-time spoken language translation.
Transportation− Truck Brake system diagnosis, vehiclescheduling, routing systems.
Software− Pattern Recognition in facial recognition, optical character recognition, etc.
10. 10
Time Series Prediction− ANNs are used to make predictions on stocks and natural
calamities.
Signal Processing−Neural networks can be trained to process an audio signal and filter it
appropriately in the hearing aids.
Control− ANNs are often used to make steering decisions of physicalvehicles.
Anomaly Detection− as ANNs are expert at recognizing patterns, they can also be trained
to generate an output when something unusual occursthat misfits the pattern.
ADVANTAGES:
A neural network can perform tasks that a linear program can do.
When an element of the neural networkfails, it can continue withoutany problem by their
parallel nature.
A neural network learns and does not need to be reprogrammed.
It can be implemented in any application.
It can be implemented without any problem.
DISADVANTAGES:
The neural network needs training to operate.
The architecture of a neural networkis different from the architecture of microprocessors
therefore needs to be emulated.
Requires high processing time forlarge neural networks.
Conclusions:
Neural networksprovide ability to provide more human-like AI.
Takes rough approximation and hard-coded reactions out of AI design (i.e. Rules
and FSMs).
Still require a lot of fine- tuning during development.