INDIAN INSTITUTE OF TECHNOLOGY,

INDORE

Project report:
ARTIFICIAL NEURAL NETWORK

SUBMITTED TO- GUNJAN RAJPUT MA’AM

SUBMITTED BY- NIDHI GOEL

RAHUL GURJAR
CONTENTS
● Introduction to Neural network
● Biological Neural Network
● Artificial Neural Network
● Neural network architecture
● Perceptron Model
● Architecture of Back propagation
Neural Networks
● “Neural” is an adjective for Neuron and “Network” represents graph like
structure.
● A neural network is a system of hardware and/or software patterned after the
operation of neurons in the human brain.
● An Artificial Neural Network (ANN) is an interconnected network of large no.
of processing elements called neurons.
● A Neural Network exhibits parallel distributed processing.
Biological Neuron Model

Dendrite: Receives signals from other neurons

Soma: Processes the information

Axon: Transmits the output of this neuron

Synapse: Point of connection to other neurons

Artificial Neuron Model
McCulloch-Pitts Neuron

● The first computational model of a neuron was proposed by Warren MuCulloch and
Walter Pitts in 1943.

● The McCulloch-Pitts neural model is also known as linear threshold gate.

● It is a neuron of a set of inputs I1, I2, I3, …, Im and output y.

 Neural Network Architecture
There are basic 3 types of architectures-

1. Single-layer feed forward network

2. Multilayer feed forward network
3. recurrent network
 Single-layer feed forward network

● In this type of network, there are only two layers, input layer and output layer.
● Input layer does not count because no computation performed in this layer.
● Output layer is formed when different weights are applied on input nodes and the
cumulative effect per node is taken.
● After this the neurons collectively give the output layer and compute the output signals.
 Multilayer feed forward network

● This layer has hidden layer which is internal to the network and has no direct contact
with the external layer.
● Existence of one or more hidden layers enable the network to be computationally
stronger, feed-forward network because information flows through the input function,
and the intermediate computations used to denote the output Z.
● There are no feedback connections in which outputs of the model are fed back into itself.
Recurrent network

● In this type of network, processing element output can be directed to the processing
element in the same layer and in the preceding layer forming a multilayer recurrent
network.
● They perform the same task for every element of a sequence, with the output being
depended on the previous computations.
● The main feature of an Recurrent Neural Network is its hidden state, which captures
some information about a sequence.
 Perceptron Model
● The perceptron model, proposed by Minsky-Papert, is a more general computational model
than McCulloch-Pitts neuron.
● It overcomes some of the limitations of the M-P neuron by introducing the concept of
numerical weights for inputs, and a mechanism for learning those weights.
● Inputs are no longer limited to boolean values like in the case of an M-P neuron, it supports
real inputs as well which makes it more useful and generalized.
 Back Propagation
● The Backpropagation neural network is a multilayered, feedforward neural network.
● Backpropagation works by approximating the non-linear relationship between the input
and the output by adjusting the weight values internally.
● It has two stages, training and testing.
● Backpropagation neural network includes an input layer, hidden layer and an output
layer. It should be noted that Backpropagation neural networks can have more than one
hidden layer.