Scribd
Upload
103 views31 pages

Artificial Neural Network

An artificial neural network is a computer program inspired by the human brain that can learn patterns in data. It is composed of artificial neurons that are linked together and process information similarly to the brain. There are three main types of learning in neural networks: supervised learning where a teacher provides expected outputs, unsupervised learning where the network learns on its own, and reinforced learning where the network receives rewards or penalties. Neural networks are widely used for applications like pattern recognition, classification, prediction, and data analysis.

Uploaded by

Pavanpreet Kaur
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
103 views31 pages

Artificial Neural Network

An artificial neural network is a computer program inspired by the human brain that can learn patterns in data. It is composed of artificial neurons that are linked together and process information similarly to the brain. There are three main types of learning in neural networks: supervised learning where a teacher provides expected outputs, unsupervised learning where the network learns on its own, and reinforced learning where the network receives rewards or penalties. Neural networks are widely used for applications like pattern recognition, classification, prediction, and data analysis.

Uploaded by

Pavanpreet Kaur
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 31

Artificial

Neural
Network

Page 1
Introduction to Artificial Neural
Network

Models of the
brain and
nervous
system

Page 2
Introduction to Artificial Neural
Network

 An Artificial Neural Network is a computer program that can


recognize pattern in a given collection of data and produce a
model for that data.

 These are highly parallel means process information much


more like brain than a serial computer.

Page 3
Inspiration from Neurobiology

The original inspiration for the term Artificial Neural


Network came from examination of Central Nervous
Systems and their
Neurons
Axons
Dendrites
Synapses

Page 4
Structure of a Neuron Page 5
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 6
Mathematical Representation

The neuron calculates a weighted sum of inputs and compares it to


a threshold. If the sum is higher than the threshold, the output is
set to 1, otherwise to -1.

Non-Linearity

Page 7
How do Artificial Neural Network work?
Desired
Input Output
Adaptive System

Cost

Error
Training algorithm

Page 8
Why we use Artificial Neural Network?

 Adaptive learning

 Self-Organization

 Real Time Operation

 Fault Tolerance via Redundant Information Coding

Page 9
Learning Methods in Artificial Neural Network

Learning Process is categorized into three parts:

 Supervised Learning

 Unsupervised Learning

 Reinforced Learning

Page 10
Supervised Learning

 A teacher is present during learning process and presents


expected output.

 Every input pattern is used to train the network.

 Learning process is based on comparison between the


calculated output and desired output.

 The error generated is used to change network parameters


that result improved performance.

Page 11
Supervised LearningPage 12
Unsupervised Learning

 No teacher is present.

 The desired output is not presented to the network.

 The system learns of it own by discovering and adapting to


the structural features in the input patterns.

Page 13
Unsupervised Learning
Page 14
Reinforced Learning

 A teacher is present but does not present the expected output


to the network.

 A reward is given for correct output and a penalty for wrong


answer.

Page 15
Reinforced Learning
Page 16
Where are ANN used?

 Recognizing and matching complicated, or in completed


pattern

 Data is unreliable

Page 17
Applications of Artificial Neural Networks

 Function approximation

 Classification

 Data mining

 Time series prediction

Page 18
Function Approximation

Function approximation:
Inputs Outputs
Create continuous input output
map

The ANN must approximate f() in order to find the appropriate output
for each set of inputs.

Page 19
Example of Function Approximation

 Use a neural network to create a model that can be used


to estimate the body density(e.g. body fat)

Two steps:

 Train the network


 Use the network

Page 20
Classification

 Similar to function approximation except that


the output is a class

On/off
Numerical Numerical
Inputs Interpret output as
Classification Outputs a class Outputs

Page 21
 Recognition

 Pattern recognition
 Character recognition
 Handwriting: processing checks

 Data association

 Not only identify the characters that were scanned


but identify when the scanner is not working properly

Page 22
 Data Conceptualization

 infer grouping relationships


e.g. extract from a database the names of those
most likely to buy a particular product.

 Data Filtering

 Planning

 Unknown environments
 Sensor data is noisy
 Fairly new approach to planning

Page 23
Types of Artificial Neural Networks

They can be distinguished by:

 Their type

 Their structure

 The learning algorithm they


use

Page 24
Types of Artificial Neural Networks

 Perceptron

 Multi-Layer- Perceptron

 Backpropagation Net

 Hopfield Net

 Kohonen Feature Map

Page 25
Perceptron

Perceptron structure

Page 26
Multi-Layer-Perceptron

Multi-Layer-
Perceptron
structure Page 27
Back propagation Net

Backpropagation
Net structure
Page 28
Hopfield Net

Hopfield Net
structure
Page 29
Kohonen Feature Map

Kohonen Feature Map


structure
Page 30
Page 31

You might also like