21
ث ي ل ث ت ب داب م و الآ و ل ع ل ا ة ي ل كInformation System

Artificial neural network

Embed Size (px)

Citation preview

Page 1: Artificial neural network

كلية العلوم و Informationاآلداب بتثليث

System

Page 2: Artificial neural network

By: Wasmeiah Theeb

Aiyd Monerah Faleh Shekhah Masoud Wasmeiah Theeb

Hezam Sarah Nasser Rajsa Nasser

:Guided byMohammed Sheraz

ARTIFICIAL NEURAL NETWORKS

Page 3: Artificial neural network

CONTENTS

INTRODUCTIONBIOLOGICAL NEURON MODELARTIFICIAL NEURON MODELARTIFICIAL NEURAL NETWORKNEURAL NETWORK ARCHITECTURESINGLE-LAYER FEED FORWARD NETWORKMULTILAYER FEED FORWARD NETWORKSLEARNING IN ANNAPPLICATIONSADVANTAGESDISADVANTAGES

Page 4: Artificial neural network

INTRODUCTION

“Neural“ is an adjective for neuron, and “network” denotes a graph like structure.

Artificial Neural Networks are also referred to as “neural nets” , “artificial neural systems”, “parallel distributed processing systems”, “connectionist systems”.

Neural networks are the simplified models of the biological neuron systems.

Neural networks are typically organized in layers. Layers are made up of a number of interconnected 'nodes' .which contain an 'activation function'.

Page 5: Artificial neural network

BIOLOGICAL NEURON MODELFour parts of a typical

nerve cell : - DENDRITES: Accepts the

inputs SOMA : Process the

inputs AXON : Turns the

processed inputs into outputs.

SYNAPSES : The electrochemical contact between the neurons.

Page 6: Artificial neural network

ARTIFICIAL NEURON MODEL

•Inputs to the network are represented by the mathematical symbol, xn

•Each of these inputs are multiplied by a connection weight , wn

sum = w1 x1 + ……+ wnxn

•These products are simply summed, fed through the transfer function, f( ) to generate a result and then output.

f

w1

w2

xn

x2

x1

wn

f(w1 x1 + ……+ wnxn)

Page 7: Artificial neural network

ARTIFICIAL NEURAL NETWORK

Artificial Neural Network (ANNs) are programs designed to solve any problem by trying to mimic the structure and the function of our nervous system.

Neural networks are based on simulated neurons, Which are joined together in a variety of ways to form networks.

Neural network resembles the human brain in the following two ways: -* A neural network acquires knowledge through learning. *A neural network’s knowledge is stored within the interconnection strengths known as synaptic weight.

Page 8: Artificial neural network

Inputs

Output

ARTIFICIAL NEURAL NETWORK

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.

Page 9: Artificial neural network

NEURAL NETWORK ARCHITECTURES

The neural network in which every node is connected to every other nodes, and these connections may be either excitatory (positive weights), inhibitory (negative weights), or irrelevant (almost zero weights).

Input node

Input node

output node

output node

Hidden node

Fig: fully connected network

These are networks in which nodes are

partitioned into subsets called layers, with no

connections from layer j to k if j > k .

Layer 1 Layer2 Layer0 Layer3

(Input layer) (Output layer)

Hidden Layer

fig: layered network

Page 10: Artificial neural network

NEURAL NETWORK ARCHITECTURES

This is the subclass of the layered networks in which there is no intra-layer connections. In other words, a connection may exist between any node in layer i and any node in layer j for i < j, but a connection is not allowed for i=j.

Fig : Acyclic network

Layer 1 Layer2 Layer0 Layer3

(Input layer) (Output layer)

Hidden Layer

Page 11: Artificial neural network

NEURAL NETWORK ARCHITECTURES

Layer 1 Layer2 Layer0 Layer3

(Input layer) (Output layer)

Hidden Layer

This is a subclass of acyclic networks in which a connection is allowed from a node in layer i only to nodes in layer i+1

fig : Feedforward network

Page 12: Artificial neural network

NEURAL NETWORK ARCHITECTURES

Many problems are best solved using neural networks whose architecture consists of several modules, with sparse interconnections between them. Modules can be organized in several different ways as Hierarchical organization, Successive refinement, Input modularity

Page 13: Artificial neural network

Neural network architecture

An artificial Neural Network is defined as a data processing system consisting of a large number of interconnected processing elements or artificial neurons. There are three fundamentally different classes of neural networks. Those are. 1. Single layer feedforward Networks. 2. Multilayer feedforward Networks. 3. Recurrent Networks.

Page 14: Artificial neural network

Single-layer Feed Forward Network

Single-layer Feedforward Networks

This kind of networking contain input layer and output layer and one layer of calculations

Page 15: Artificial neural network

Multilayer Feedforward Networks

Multilayer Feedforward Networks

This type of network contains several layers and separated from the first type is the hidden layers that areProcessing

Page 16: Artificial neural network

Learning in ANN

Learning methods in neural networks can be broadly classified in three basic types. - Supervised Learning - Unsupervised Learning - Reinforcement LearningSupervised Learning:- 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 outputs

Errors are then calculated, causing the system to adjust the weights which control the network.

Here a teacher is assume to be present during the learning process..

Neural networks are not programmed but it is education and there are many of them learning algorithms Back

Propagation algorithm (an algorithm based propagation of errors from back to front to set the network) weights and

method of Hebb Rule.

Page 17: Artificial neural network

Learning in ANN

Unsupervised Learning:- Here the target output is not presented to the

network, Because there is no teacher to present the described patterns.

So the system learns of its own by discovering and adapting to structural features of the input patterns.

Reinforcement Learning:- In this method, a teacher though available, does

not present the expected answer but only indicates if the computed output is correct or incorrect.

The information provided helps the network in its learning process.

Here a reward is given for correct answer computed and a penalty for a wrong answer.

Page 18: Artificial neural network

APPLICATIONS OF NEURAL NETWORKS

Character Recognition:- Neural networks can be used to recognize handwritten characters.

Image Compression:- Neural networks can receive and process vast amounts of information at once, making them useful in image compression.

Stock Market Prediction:- Neural networks can examine a lot of information quickly and sort it all out, they can be used to predict stock prices.

Travelling Salesman Problem:- Neural networks can solve the traveling salesman problem, but only to a certain degree of approximation.

Security and Loan Applications:- With the acceptation of a neural network that will decide whether or not to grant a loan.

Page 19: Artificial neural network

1.Pattern recognition2.Investment analysis3.Control systems &4. monitoring5.Marketing and financial applications6.Mobile computing7.Forecasting – sales, market research, meteorology

APPLICATIONS OF NEURAL NETWORKS

Page 20: Artificial neural network

: ADVANTAGES

A neural network can perform tasks that a linear program can not.When an element of the neural network fails, it can continue without any 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

Page 21: Artificial neural network

DISADVANTAGES

The architecture of a neural network is different from the architecture of microprocessors therefore needs to be emulated.

Requires high processing time for large neural networks The neural network needs training to operate.