You are on page 1of 36

Artificial Neural Network

Guided By Miss Jagruti Goswami

Submitted By Jitendra Patel Miral Patel 6th IT

C.U.SHAH COLLEGE OF ENGG. & TECH. WADHWAN CITY 363 030

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

WADHWAN CITY
DIST : SURENDRANAGAR

CERTIFICATE

This is to certify that Mr. Jitendra Patel and Mr.Miral Patel Studying in SEM VI of B.E. Information Technology having Roll-No 31 & 34 has completed his seminar on the following topic successfully

Topic Name: ARTIFICIAL NEURAL NETWORK

Staff In charge Date : ___________

Head of Dept. (Miss Saroj Bodar)

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

ACKNOWLEDGEMENT
I hereby take this opportunity to thank each and everyone who has helped me in creating and formulating this seminar report. I especially thank to our H.O.D Miss S.G.Bodar and our lab-incharge Miss Jagruti madam for giving me the moral and academic support for representing the seminar. At last I would like to thank all those who directly or indirectly helped me in preparing the seminar report.

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

INDEX
Content No.
1. 2. 3. 4. 5. 6. Introduction Definition Structure Of Human Brain Neurons Basics Of ANN Model Artificial Neural Networks 6.1 How ANN Differs From Conventional Comp. 6.2 ANN Vs Von Neumann Comp. 7. Perceptron 8. Learning Laws 8.1 Hebbs Rule 8.2 Hopfield Rule 8.3 The Delta Rule 8.4 The Gradient Descent Rule 8.5 Kohonens Learning Rule 9. Basic Structure Of ANNS 10. Network Architectures 10.1Single Layer Feed Forward ANN 10.2Multilayer Feed forward ANN 10.3Recurrent ANN 11. Learning Of ANNS 11.1Learning With A Teacher 11.2Learning Without A Teacher 11.3Learning Tasks 12. Control 13. Adaptation 14. Generalization 15. Probabilistic ANN 16. Advantages 17. Limitations 18. Applications 19. References 1 2 3 4 6 7 10 11

Page

14 15

18

23 24 24 25 26 27 28 32

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

Artificial Neural Network

Introduction
Ever since eternity, one thing that has made human beings stand apart from the rest of the animal kingdom is, its brain .The most intelligent device on earth, the Human brain is the driving force that has given us the ever-progressive species diving into technology and development as each day progresses. Due to his inquisitive nature, man tried to make machines that could do intelligent job processing, and take decisions according to instructions fed to it. What resulted was the machine that revolutionized the whole world, the Computer (more technically speaking the Von Neumann Computer). Even though it could perform millions of calculations every second, display incredible graphics and 3-dimentional animations, play audio and video but it made the same mistake every time. Practice could not make it perfect. So the quest for making more intelligent device continued. These researches lead to birth of more powerful processors with high-tech equipments attached to it, super computers with capabilities to handle more than one task at a time and finally networks with resources sharing facilities. But still the problem of designing machines with intelligent self-learning, loomed large in front of mankind. Then the idea of initiating human brain stuck the designers who started their researches one of the technologies that will change the way computer work Artificial Neural Networks.

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

Definition
Neural Network is the specified branch of the Artificial Intelligence. In general, Neural Networks are simply mathematical techniques designed to accomplish a variety of tasks. Neural Networks uses a set of processing elements (or nodes) loosely analogues to neurons in the brain (hence the same, neural networks). These nodes are interconnected in a network that can then identify patterns in data as it is exposed to the data. In a sense, the network learns from the experience just as people do. Neural networks can be configured in various arrangements to perform a range of tasks including pattern recognition, data mining, classification, and process modeling.

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

Structure of human brain


As stated earlier, Neural Networks is very much similar to the biological structure of human Brain. Following is the biological structure of brain is given.

Sequential Functions: Rules Concepts Calculations Expert Systems Learn by Rules

Parallel Functions: Images Pictures Control Neural Networks Learn by experience

Functions of Brain As shown in figure, left part of the brain consists of rules, concepts and calculations. It follows Rule Based Learning and hence solves the problem by passing them through rules. It has sequential pairs of Neurons. Therefore, this part of brain is similar to the expert systems. Right part of the brain, as shown below in the figure; consist of functions, images, pictures, and controls. It follows parallel learning and hence learns through experience. It has parallel pairs of Neurons. Therefore, this brain is similar to the Neural Network.

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

Neurons
The conceptual constructs of a neural network stemmed from our early understanding of the human brain. The brain is comprised of billion and billions of interconnected neurons (some experts estimate upwards of 1011 neurons in the human brain). The fundamental building blocks of this massively parallel cellular structure are really quite simply when studied in isolation. A neuron receives incoming electrochemical signals from its dendrites and collects these signals at the neuron nucleus. The neuron nucleus has a internal threshold that determines if neuron itself tires in response to the incoming information. If the combined incoming signals exceeds this threshold then neuron fires and an electrochemical signal is sent to all neurons connected to the firing neuron on its output connections or axons. Otherwise the incoming signals are ignored and the neuron remains dormant. There are many types of neurons or cells. From a neuron body (soma) many fine branching fibers, called dendrites, protrude. The dendrites conduct signals to the soma or cell body. Extending from a neurons soma, at a point called axon hillock (initial segment), is a long giber called an axon, which generally splits into the smaller branches of axonal arborization. The tips of these axon branches (also called nerve terminals, end bulbs, telondria) impinge either upon the dendrites, somas or axons of other neurons or upon effectors.

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

The axon-dendrite (axon-soma, axon-axon) contact between end bulbs and the cell it impinges upon is called a synapse. The signal flow in the neuron is (with some exceptions when the flow could be bi-directional) from the dendrites through the soma converging at the axon hillock and then down the axon the the end bulbs. A neuron typically has many dendrites but only a single axon. Some neurons lack axons, such as the amacrine cells.

C.U.Shah College of Engg. & Tech.

Artificial Neural Network

Basics of Artificial Neural Models


The human brain is made up of computing elements, called neurons, coupled with sensory receptors (affecters) and effectors. The average human brain, roughly three pounds in weight and 90 cubic inches in volume, is estimated to contain about 100 billion cells of various types. A neuron is a special cell that conducts and electrical signal, and there are about 10 billion neurons in the human brain. The remaining 90 billion cells are called glial or glue cells, and these serve as support cells for the neurons. Each neuron is about one-hundredth size of the period at the end of this sentence. Neurons interact through contacts called synapses. Each synapse spans a gap about a millionth of an inch wide. On the average each neuron receives signals via thousands of synapses. The motivation for artificial neural network (ANN) researches is the belief that a humans capabilities, particularly in real-time visual perception, speech understanding, and sensory information processing and in adaptively as well as intelligent decision making in general, come from the organizational and computational principles exhibited in the highly complex neural network of the human brain. Expectations of faster and better solution provide us with the challenge to build machines using the same computational and organizational principles, simplified and abstracted from neurobiological of the brain.

Artificial Neural Network Model

C.U.Shah College of Engg. & Tech.

10

Artificial Neural Network

Artificial Neural Network


Artificial neural network (ANNs), also called parallel distributed processing systems (PDPs) and connectionist systems, are intended for modeling the organization principles of the central neurons system, with the hope that the biologically inspired computing capabilities of the ANN will allow the cognitive and logically inspired computing capabilities of the ANN will allow the cognitive and sensory tasks to be performed more easily and more satisfactory than with conventional serial processors. Because of the limitation of serial computers, much effort has devoted to the development of the parallel processing architecture; the function of single processor is at a level comparable to that of a neuron. If the interconnections between the simplest fine-grained processors are made adaptive, a neural network results. ANN structures, broadly classified as recurrent (involving feedback) or non-recurrent (without feedback), have numerous processing elements (also dubbed neurons, neurodes, units or cells) and connections (forward and backward interlayer connections between neurons in different layers, forward and backward interlayer connections or lateral connections between neurons in the same layer, and self-connections between the input and output layer of the same neuron. Neural networks may not have differing structures or topology but are also distinguished from one another by the way they learn, the manner in which computations are performed (rule-based, fuzzy, even nonalorithmic), and the component characteristic of the neurons or the input/output description of the synaptic dynamics). These networks are required to perform significant processing tasks through collective local interaction that produces global properties. Since the components and connections and their packaging under stringent spatial constraints make the system large-scale, the role of graph theory, algorithm, and neuroscience is pervasive.

C.U.Shah College of Engg. & Tech.

11

Artificial Neural Network

How Neural Networks differ from Conventional Computer?


Neural Networks perform computation in a very different way than conventional computers, where a single central processing unit sequential dictates every piece of the action. Neural Networks are built from a large number of very simple processing elements that individually deal with pieces of a big problem. A processing element (PE) simply multiplies an output value (table lookup). The principles of neural computation come from the massive processing tasks, and from the adaptive nature of the parameters (weights) that interconnected the PEs.

C.U.Shah College of Engg. & Tech.

12

Artificial Neural Network

Similarities and difference between neural net and von Neumann computer
Neural net Trained (learning by example) by adjusting the connection strengths, threshold, and structure) Memory and processing elements separate are collected Parallel(discrete or continuous), digital, asynchronous May be fault-tolerant because of Distributed representation and Large scale redundancy Self-organization during learning Knowledge stored is adaptable address Information is stored in the Interconnection between neurons Processing is anarchic Cycle time, which governs Processing speed, occurs in Millisecond range memory location is strictly replaceable processing is autocratic cycle time, corresponds to processing one step of a program in the cpu during One clock cycle , occurs In the nanosecond range Software dependent Knowledge stored in an Sequential or serial , Memory and processing Von Neumann computer Programmed with instruction ( if-then analysis based on logic)

synchronous(with a clock) Not fault- talerant

C.U.Shah College of Engg. & Tech.

13

Artificial Neural Network

Perceptron
At the heart of every Neural Network is what is referred to as the perceptron (sometimes called processing element or neural node) which is analogus to the neuron nucles in the brain. The second layer that is very first hidden layer is known as perceptron. As was the case in the brain the operation of the perceptron is very simple; however also as is the case in the brain, when all connected neurons operate as a collective they can provide some very powerful learning capacity. Input signals are applied to the node via input connection (dendrites in the case of the brain.) The connections have strength which change as the system learns. In neural networks the strength of the connections are referred to as weights. Weights can either excite or inhibite the transmission of the incoming signal. Mathematically incoming signals values are multiplied by the value of those particular weights. At the perceptron all weighted input are summed. This sum value is than passed to a scaling function. The selection of scaling function is part of the neural network design. The structure of perceptron (Neuron Node) is as follow.

Perceptron

C.U.Shah College of Engg. & Tech.

14

Artificial Neural Network

Learning Laws
Many learning laws are in common use. Most of these are some sort of variation of the best known and oldest learning laws, hebbs rule. Research into different learning functions continues as new ideas routine show up in trade publication. Some researches have the modeling of biological learning as their main objective. Others are experimenting with adaptation of their perceptions of how nature handles learning. Either way, mans understanding of how neural processing actually works is very limited. Learning is certainly more complex rhan the simplification represented by the learning laws currently develop. A few of the major laws are presented as examples. Hebbs Rule The first, and undoubtedly the best known, learning rule were introduced by Donald Hebb. The description appeared in his book the Organization of behavior in 1949. His basic rule is: if a neuron receives an input from another neuron, and if both are highly active (mathematically have the same sign), the weight between the neurons should be strengthened. Hopfield Law It is similar to Hebbs rule with the exception that it specifies the magnitude of the strengthening or weakening. It states, if the desired output and the input are both active and both inactive, increment the connection weight by the learning rate, otherwise decrement the weight by the learning rate.

The Delta Rule


This rule is a further variation of Hebbs Rule. It is one of the most commonly used. This rule is based on the simple idea of continuously modifying the strengths of the input connections to reduce the difference (the delta) between the desired output value and the actual output of a

C.U.Shah College of Engg. & Tech.

15

Artificial Neural Network

processing element. Their rule changes the synaptic weights in the way that minimizes the mean squared error of the network. This rule is also referred to as windrows-Hoff Learning rule and the least mean square (LMS) Learning Rule. The way that the Delta Rule works is that the delta rule error in the output layer is transformed by the derivative of the transfer function and is then used in the previous neural layer to adjust input connection weights. In other words, the back-propagated into previous layers one layer at a time. The process of back-propagating the network errors continues until the first layer is reached. The network typed called feed forward; back-propagation derives its name from this method of computing the error term. When using the delta rule, it is important to ensure that the input data set is well randomized. Well-ordered or structured presentation of the training set can lend to a network, which cannot converge to the desired accuracy. If that happens, then network is incapable of learning the problem. The Gradient Descent Rule This rule is similar to the Delta rule in that the derivatives of the transfer function is still used to modify the delta error before it is applied to the connection weights. Here, however, an additional proportional constant tied to the learning rate is appended to the final modifying factor acting upon the weights. This rule is commonly used, even though it converges to a point of stability very slowly. It has been shown that different learning rates for different layers of network help the learning process converge faster. In these tests, the learning rates for those layers close to the output were set lower than those layers near the input. This especially important for applications where the input data is not derived from a strong underlying model. Kohonens Learning Law The procedure, developed by Teuvo Kohonen, was inspired by learning in biological systems. In this procedure, the processing elements complete for

C.U.Shah College of Engg. & Tech.

16

Artificial Neural Network

the opportunity to learn, or update their weights. The processing element with the largest output is declared the winner and has the capabilities of inhibiting its competitors as well as exciting its neighbors. Only the winner is permitted an output, and only the winner plus its neighbors are allowed to adjust their connection weights. Further, the size of the neighborhood can vary during the training period. The usual paradigm is to start with a larger definition of the neighborhood, and narrow in as the training process proceeds. Because the winning element is defined as the one that has the closest match to the input pattern, Kohonen networks model the distributed of the data and is sometimes refered to as self-organizing maps or selforganizing topologies.

C.U.Shah College of Engg. & Tech.

17

Artificial Neural Network

Basic Structure of artificial neural network


input layer: The bottom layer is known as input neuron network in this case x1 to x5 are input layerneurons. Hidden layer: The in-between input and output layer the layers are knownas hidden layers where the knowledge of past experience / training is the Output Layer: The topmost layer which give the final output. In this case z1 and z2 are output neurons.

Basic Structure Of Artificial Neural Network

C.U.Shah College of Engg. & Tech.

18

Artificial Neural Network

Network architectures
1). Single layer feedforword networks: In this layered neural network the neurons are organized in the form of layers. In this simplest form of a layered network, we have an input layer of source nodes those projects on to an output layer of neurons, but not vise-versa. In other words, this network is strictly a feed forward or acyclic type. It is as shown in figure:

Such a network is called single layered network, with designation single later referring to the o/p layer of neurons. 2). Multilayer feed forward networks: The second class of the feed forward neural network distinguishes itself by one or more hidden layers, whose computation nodes are correspondingly called neurons

C.U.Shah College of Engg. & Tech.

19

Artificial Neural Network

or units. The function of hidden neurons is intervenue between the external i/p and the network o/p in some useful manner. The ability of hidden neurons is to extract higher order statistics is particularly valuable when the size of i/p layer is large. The i/p vectors are feedforward to 1st hidden layer and this pass to 2nd hidden layer and so on until the last layer i.e. output layer, which gives actual network response.

3). Recurrent networks: A recurrent network distinguishes itself from feed forward neural network, in that it has least one feed forward loop. As shown in figures output of the neurons is fed back into its own inputs is referred as self-feedback A recurrent network may consist of a single layer of neurons with each neuron feeding its output signal back to the inputs of all the other neurons. Network may have hidden layers or not.

C.U.Shah College of Engg. & Tech.

20

Artificial Neural Network

C.U.Shah College of Engg. & Tech.

21

Artificial Neural Network

Learning of ANNS
The property that is of primary significance for a neural network is the ability of the network to learn from environment, and to improve its performance through learning. A neural network learns about its environment through an interactive process of adjustment applied to its synaptic weights and bias levels. Network becomes more knowledgeable about its environment after each iteration of the learning process.

Learning with a teacher:


1). Supervised learning: the learning process in which the teacher teaches the network by giving the network the knowledge of environment in the form of sets of the inputsoutputs pre-calculated examples. As shown in figure

C.U.Shah College of Engg. & Tech.

22

Artificial Neural Network

Neural network response to inputs is observed and compared with the predefined output. The difference is calculated refer as error signal and that is feed back to input layers neurons along with the inputs to reduce the error to get the perfect response of the network as per the predefined outputs.

Learning without a teacher:


Unlike supervised learning, in unsupervised learning, the learning process takes place without teacher that is there are no examples of the functions to be learned by the network. 1). Reinforcement learning / neurodynamic programming In reinforcement learning, the learning of an input output mapping is performed through continued interaction with environment in order to minimize a scalar index of performance. As shown in figure.

C.U.Shah College of Engg. & Tech.

23

Artificial Neural Network

In reinforcement learning, because no information on way the right output should be provided, the system must employ some random search strategy so that the space of plausible and rational choices is searched until a correct answer is found. Reinforcement learning is usually involved in exploring a new environment when some knowledge( or subjective feeling) about the right response to environmental inputs is available. The system receives an input from the environment and process an output as response. Subsequently, it receives a reward or a panelty from the environment. The system learns from a sequence of such interactions. 2). Unsupervides learning: in unsupervised or self-organized learning there is no external teacher or critic to over see the learning process.

As indicated in figure.

Rather provision is made for a task independent measure of the quality of the representation that the network is required to learn and the free parameters of the network are optimized with respect to that measure. Once the network has become tuned to the statistical regularities of the input data, it developes the ability to form internal representation for encoding features of the input and there by to create the new class automatically.

C.U.Shah College of Engg. & Tech.

24

Artificial Neural Network

Learning tasks Pattern recognition: Humans are good at pattern recognition. We can recognize the familiar face of the person even though that person has aged since last encounter, identifying a familiar person by his voice on telephone, or by smelling the fragments comes to know the food etc. Pattern recognition is formally defined as the process where by a received pattern/signal is assigned to one of a prescribed number of classes. A neural network performs pattern recognition by first undergoing a training session, during which the network is repeatedly present a set of input pattern along with the category to which each particular pattern belongs. Later, a new pattern is presented to the network that has not been seen before, but which belongs to the same pattern caterogy used to train the network. The network is able to identify the class of that particular pattern because of the information it has extracted from the training data. Pattern recognition performed by neural network is statistical in nature, with the pattern being represented by points in a multidimensional decision space. The decision space is divided into regions, each one of which is associated with class. The decision boundries are determined by the training process.

C.U.Shah College of Engg. & Tech.

25

Artificial Neural Network

As shown in figure: in generic terms, pattern-recognition machines using neural network may take two forms. 1). To extract features through unsupervised network. 2). Features pass to supervised network for pattern classification to give final output.

C.U.Shah College of Engg. & Tech.

26

Artificial Neural Network

Control The control of a plant is another learning task that can be done by a neural network; by a plant we mean a process or critical part of a system that is to be maintained in a controlled condition. The relevance of learning to control should not be surprising because, after all, the human brain is a computer, the output of which as a whole system are actions. In the context of control, the brain is living proof that it is possible to build a generalized controller that takes full advantages of parallel distributed hardware, can control many thousands of processes as done by the brain to control the thousands of muscles.

C.U.Shah College of Engg. & Tech.

27

Artificial Neural Network

Adaptation The environment of the interest is no stationary, which means that the statistical parameters of the information bearing generated by the environment vary with the time. In situation of the kind, the traditional methods of supervised may learning may prove to be inadequate because the network is not equipped with the necessary means to track the statistical variation of the environment in which it operates. To overcome these shortcomings, it is desirable for a neural network to continually adapt its free parameters to variation in the incoming signals in a real time fashion. Thus an adaptive system responds to every distinct input as a novel one. In other words the learning process encountered in the adaptive system never stops, with learning going on while signal processing is being performed by the system. This form of learning is called continuous learning or learning on the fly. Generalization In back propagation learning we typically starts with a training sample and uses the back propagation algorithm to compute the synaptic weights of a multiplayer preceptor by loading (encoding) as many as of the training example as possible into the network. The hope is that the neural network so design will generalize. A network is said generalize well when the input output mapping computed by the network is correct or nearly so for the test data never used in creating or training the network; the term generalization is borrowed from psychology. A neural network that is design to generalize well will produced a correct input output mapping even when the input is slightly different from the examples used to train the network. When however a neural network learns too many input output examples the network may end up memorizing the training data. It may do so by finding a feature that is present in training

C.U.Shah College of Engg. & Tech.

28

Artificial Neural Network

data but not true for the underlining function that is to be modeled. Such a phenomena is referred to as an over fitting or over training. When the network is over trained it looses the ability to generalize between similar input output pattern. The probabilistic neural network Another multilayer feed forward network is the probabilistic neural network (PNN). In addition to the input layer, the PNN has two hidden layers and an output layer. The major difference from a feed forward network trained by back propagation is that it can be constructed after only a single pass of the training exemplars in its original form and two passes is a modified version. The activation function of a neural in the case of the PNN is statistically derived from estimating of probability density functions (PDFs) based on training patterns.

C.U.Shah College of Engg. & Tech.

29

Artificial Neural Network

Advantages of Neural Networks 1) Networks start processing the data without any preconceived hypothesis. They start random with weight assignment to various input variables. Adjustments are made based on the difference between predicted and actual output. This allows for unbiased and batter understanding of data. 2) Neural networks can be retained using additional input variables and number of individuals. Once trained thay can be called on to predict in a new patient. 3) There are several neural network models available to choose from in a particular problem. 4) Once trained, they are very fast. 5) Due to increased accuracy, results in cost saving. 6) Neural networks are able to represent any functions. Therefore they are called Universal Approximators. 7) Neural networks are able to learn representative examples by back propagating errors.

C.U.Shah College of Engg. & Tech.

30

Artificial Neural Network

Limitations of Neural Network Low Learning Rate:- >> For problems requiring a large and complex network architecture or having a large number of training examples, the time needed to train the network can become excessively long.

Forgetfulness :->> The network tends to forget old training examples as it is presented with new ones. A previously trained neural network that must be updated with new information must be trained using the old and new examples there is currently no known way to incrementally train the network.

Imprecision :->> Neural networks do not provide precise numerical answer, but rather relate an input pattern to the most probable output state.

Black box approach :->> Neural networks can be trained to transform an input pattern to output but provide no insights to the physics behind the transformation.

Limited Flexibility :->> The ANNS is designed and implemented for only one particular system. It is not applicable to another system.

C.U.Shah College of Engg. & Tech.

31

Artificial Neural Network

Application Of Artificial Neural Network

In parallel with the development of theories and architectures for neural networks the scopes for applications are broadening at a rapid pace. Neural networks may develop intuitive concepts but are inherently ill suited for implementing rules precisely, as in the case of rule based computing. Some of the decision making tools of the human brain such as the seats of consciousness, thought, and intuition, do not seem to be within our capabilities for comprehension in the near future and are dubbed by some to be essentially no algorithmic. Following are a few applications where neural networks are employed presently: 1) Time Series Prediction Predicting the future has always been one of humanitys desires. Time series measurements are the means for us to characterize and understand a system and to predict in future behavior. Gershenfield and weighed defined three goals for time series analysis: forecasting, modeling, and characterization. Forecasting is predicting the short-term evolution of the system. Modeling involves finding a description that accurately captures the features of the long-term behavior. The goal of characterization is to determined the fundamental properties of the system, such as the degrees of freedom or the amount of randomness. The traditional methods used for time series prediction are the moving average (ma), autoregressive (ar), or the combination of the two, the ARMA model. Neural network approaches produced some of the best short-term predictions. However, methods that reconstruct the state space by timedelay embedding and develop a representation for the geometry in the systems state space yielded better longer-term predictions than neural networks in some cases.

C.U.Shah College of Engg. & Tech.

32

Artificial Neural Network

2) Speech Generation One of the earliest successful applications of the back propagation algorithm for training multiplayer feed forward networks were in a speech generation system called NET talk, developed by Sejnowski and Rosenberg. Net talk is a fully connected layered feed forward network with only one hidden layer. It was trained to pronounce written English text. Turning a written English text into speech is a difficult task, because most phonological rules have exceptions that are context-sensitive. Net talk is a simplest network that learns the function in several hours using exemplars.

3) Speech Recognition Kohonen used his self-organizing map for inverse problem to that addressed by Net talk: speech recognition. He developed a phonetic typewriter for the Finnish language. The phonetic typewriter takes as input a speech as input speech and converts it into written text. Speech recognition in general is a much harder problem that turning text into speech. Current state-of-the-art English speech recognition systems are based on hidden Markov Model (HMM). The HMM, which is a Markov process; consist of a number of states, the transitions between which depend on the occurrence of some symbol. 4) Autonomous Vehicle Navigation Vision-based autonomous vehicle and robot guidance have proven difficult for algorithm-based computer vision methods, mainly because of the diversity of the unexpected cases that musy be explicitly dealt with in the algorithms and the real-time constraint. Pomerleau successfully demonstrated the potential of neural networks for overcoming these difficulties. His ALVINN (Autonomous Land Vehicle in Neural Networks) set a worked record for autonomous navigation distance. After training on a two-mile stretch of highway, it

C.U.Shah College of Engg. & Tech.

33

Artificial Neural Network

drove the CMU Navlab, equipped with video cameras and laser range sensors, for 21.2 miles with an average speed of 55 mph on a relatively old highway open to normal traffic. ALVINN was not distributed by passing cars while it was driven autonomously. ALVINN nearly doubled the previous distance world record for autonomous navigation. A network in ALVINN for each situation consists of a single hidden layer of only four units, an output layer of 30 units and a 30 X 32 retina for the 960 possible input variables. The retina is fully connected to the hidden layer, and the hidden layer is fully connected to the output layer. The graph of the feed forward network is a node-coalesced cascade version of bipartite graphs. 5) Handwriting Recognition Members of a group at AT&T Bell Laboratories have been working in the area of neural networks for many years. One of their projects involves the development of a neural network recognizer for handwritten digits. A feed forward layered network with three hidden layers is used. One of the key features in this network that reduces the number of free parameters to enhance the probability of valid generalization by the network. Artificial neural network is also applied for image processing. 6) In Robotics Field: With the help of neural networks and artificial Intelligence. Intelligent devices, which behave like human, are designed. Which are helpful to human in performing various tasks.

C.U.Shah College of Engg. & Tech.

34

Artificial Neural Network

Following are some of the application of Neural Networks in various fields: Business o Marketing o Real Estate Document and Form Processing o Machine Printed Character Recognition o Graphics Recognition o Hand printed Character Recognition o Cursive Handwriting Character Recognition Food Industry o Odor/Aroma Analysis o Product Development o Quality Assurance Financial Industry o Market Trading o Fraud Detection o Credit Rating Energy Industry o Electrical Load Forecasting o Hydroelectric Dam Operation o Oil and Natural Gas Company Manufacturing o Process Control o Quality Control Medical and Health Care Industry o Image Analysis o Drug Development o Resource Allocation Science and Engineering

C.U.Shah College of Engg. & Tech.

35

Artificial Neural Network

o Chemical Engineering o Electrical Engineering

At last I want to say that after 200 or 300 years neural networks is so developed that it can find the errors of even human beings and will be able to rectify that errors and make human being more intelligent.

Reference: Artificial Neural Network By :- Robert j Schalkoff Neural Network By: - Simon Haykin Internet: www.anns.mit/edu.com www.cs.barkely.com www.academicresources.com

C.U.Shah College of Engg. & Tech.

36