You are on page 1of 14

ARTIFICIAL INTELLIGENCE

EL40102
CONTENTS

֍ Biological Neuron
֍ Artificial Neuron
֍ Activation Function
֍ Single Layer Perceptron
֍ Multi Layer Perceptron
֍ Back Propagation Algorithm
֍ Recurrent Neural Network
֍ Adaptive Resonance Theory

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 2
Odisha
Unit – 1 Lecture 4
Objective of Today’s Lecture
Understand the concept of Perceptron

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 3
Odisha
Rosenblatt’s Perceptron
Introduction

 The perceptron is a single processing unit of any neural network.


 Frank Rosenblatt first proposed in 1958 is a simple neuron which is used to classify its input into
one or two categories.
 Perceptron is a linear classifier, and is used in supervised learning.
 It helps to organize the given input data.
 A perceptron is a neural network unit that does a precise computation to detect features in the input
data.
 Perceptron is mainly used to classify the data into two parts.
 It is also known as Linear Binary Classifier.

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 4
Odisha
Rosenblatt’s Perceptron
Introduction

 Single Layer Perceptron

 Multi-Layer Perceptron

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 5
Odisha
Rosenblatt’s Perceptron
Single Layer Perceptron

 The simplest form of neural network.


 A computational model of the retina of the eye.
 Can be used to classify linearly separable
patterns.
 Network comprises of three units.
 Sensory Unit, S
 Association Unit, A
 Response Unit, R

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 6
Odisha
Rosenblatt’s Perceptron
Sensory Unit, S

 400 photodetectors receives input images


 Provides a 0 / 1 electric signal as output.
 If the input signals exceed a threshold, then the
photodetector outputs 1 else 0.

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 7
Odisha
Rosenblatt’s Perceptron
Association Unit, A

 Comprises feature demons or predicates.


 The predicate examine the output of the S unit
for specific feature of the image.

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 8
Odisha
Rosenblatt’s Perceptron
Response Unit, R

 Comprises pattern recognizers or perceptrons.


 Receives the results of the predicate, binary form.

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 9
Odisha
Rosenblatt’s Perceptron
A Simple Perceptron Model

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 10
Odisha
Rosenblatt’s Perceptron
A Simple Perceptron Model

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 11
Odisha
Rosenblatt’s Perceptron
Multilayer Perceptron

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 12
Odisha
ADALINE
 ADAptive LInear Neural Element Network.
 Framed by Bernard Widrow of Stanford University.
 It is also called as single-layer neural network.

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 13
Odisha
MADALINE
 Many ADALINE.

Asutosh Patnaik, Asst. Prof., Dept. of EEE, CGU,


10-08-2022 14
Odisha

You might also like