This document provides an overview of artificial neural networks. It describes the biological neuron model that inspired artificial networks, with dendrites receiving inputs, the soma processing them, the axon transmitting outputs, and synapses connecting neurons. An artificial neuron model is presented that uses weighted inputs, a summation function, and an activation function to generate outputs. The document discusses unsupervised and supervised learning methods, and lists applications such as character recognition, stock prediction, and medicine. Advantages include human-like thinking and handling noisy data, while disadvantages include the need for training and high processing times.

2. Contents
 Intoduction
 Artifcial Neural Network
 Biological Neuron Model
 Artificial Neuron Model
 Applications
 Advantages
 Disadvantages

3. Introduction
 Artificial Neural Network(ANN) is a computing
system made up of a number of simple, highly
interconnected processing elements, which process
information by their dynamic state response to
external inputs.
 They are desigend by inspiration from the
biological neural system

4. BIOLOGICAL NEURON MODEL
Four 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

5. 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 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.

6. 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

7. Learning
 In artificial neural networks, learning refers to the method
of modifying the weights of connections between the
nodes of a specified network.
 The learning ability of a neural network is determined by
its architecture and by the algorithmic method chosen for
training.
 They are of two types.

8.  This is learning by doing.
 In this approach no sample
outputs are provided to the
network against which it
can measure its predictive
performance for a given
vector of inputs.
UNSUPERVISED LEARNING
• A teacher is available
• The training data consist of
pairs of input and desired
output values that are
traditionally represented in
data vectors.
SUPERVISED LEARNING

9. Applications
 Character Recognization
 Image Compression
 Stock Market Pridiction
 Medicine, Electronic Nose,
Security, and Loan
Applications

10. Advantages
 It involves human like thinking.
 They handle noisy or missing data.
 They can work with large number of variables or
parameters.
 They provide general solutions with good predictive
accuracy.
 System has got property of continuous learning.

11. Disadvantages
 Needs training to operate
 Architecture of NN is different from the architecture
of microprocessor.Therefore needs to be emulated
 Requires high processing time for large networks