Presentation is loading. Please wait.

Presentation is loading. Please wait.

Lecture 02: Perceptron By: Nur Uddin, Ph.D.

Published byCharles McGee Modified over 5 years ago

Similar presentations

Presentation on theme: "Lecture 02: Perceptron By: Nur Uddin, Ph.D."— Presentation transcript:

1 Lecture 02: Perceptron By: Nur Uddin, Ph.D

2 History Artificial Intelligent - Lecture 2

3 History Pioneering work on neural network:
McCulloch and Pitts (1943) for introducing the idea of neural networks as computing machines. Hebb (1949) for postulating the first rule for self-organized learning. Rosenblatt (1958) for proposing the perceptron as the first model for learning with a teacher (i.e., supervised learning). Artificial Intelligent - Lecture 2

4 Perceptron The perceptron is the simplest form of a neural network.
It is used to classify linearly separable patterns. The learning algorithm was developed by Rosenblatt (1958, 1962) for his perceptron brain model. Artificial Intelligent - Lecture 2

5 Linearly Separable Patterns
Artificial Intelligent - Lecture 2

6 Perceptron Model Rosenblatt’s perceptron is built around a nonlinear neuron, namely, the McCulloch–Pitts model of a neuron. Exercise: Calculate the output ! Artificial Intelligent - Lecture 2

7 Mathematics Model of Perceptron
Artificial Intelligent - Lecture 2

8 Classification Question 1: How to make classification? Question 2:
What is the activation function? Artificial Intelligent - Lecture 2

9 Decision Boundary Artificial Intelligent - Lecture 2

10 Learning Algorithm Artificial Intelligent - Lecture 2

11 Example 1: Restaurants Survey
Price Taste Buy ? 5 6 Yes 7 3 No 8 9 10 Artificial Intelligent - Lecture 2

12 Example 1: Restaurants Survey (Cont’d)
Price Taste Buy ? 5 6 1 7 3 8 9 10 Artificial Intelligent - Lecture 2

13 Classification using Perceptron
Training Test (Generalization) Artificial Intelligent - Lecture 2

14 Example 1: Grading System
Mid Final Score Grade 60 50 54 Fail 70 64 Pass 40 80 65 63 62 58 55 59 30 56 90 Score = Mid exam: 40% Final exam: 60% Grading system = Pass: score ≥ 60 Fail : score < 60 Artificial Intelligent - Lecture 2

15 Example 1: Grading System
Mid Final Score Grade 60 50 54 Fail 70 64 Pass 40 80 65 63 62 58 55 59 30 56 90 Score = Mid exam: 40% Final exam: 60% Grading system = Pass: score ≥ 60 Fail : score < 60 Artificial Intelligent - Lecture 2

16 Exercise 1: Airlines Passenger Survey (Economy Class)
Artificial Intelligent - Lecture 2

Download ppt "Lecture 02: Perceptron By: Nur Uddin, Ph.D."

Similar presentations

Perceptron Lecture 4.

Perceptron Lecture 4.
Introduction to Neural Networks 2. Overview  The McCulloch-Pitts neuron  Pattern space  Limitations  Learning.

Introduction to Neural Networks 2. Overview  The McCulloch-Pitts neuron  Pattern space  Limitations  Learning.
1 Machine Learning: Lecture 4 Artificial Neural Networks (Based on Chapter 4 of Mitchell T.., Machine Learning, 1997)

1 Machine Learning: Lecture 4 Artificial Neural Networks (Based on Chapter 4 of Mitchell T.., Machine Learning, 1997)
G53MLE | Machine Learning | Dr Guoping Qiu

G53MLE | Machine Learning | Dr Guoping Qiu
Artificial Neural Networks (1)

Artificial Neural Networks (1)
Perceptron Learning Rule

Perceptron Learning Rule
NEURAL NETWORKS Perceptron

NEURAL NETWORKS Perceptron
Artificial Neural Network

Artificial Neural Network
5/16/2015Intelligent Systems and Soft Computing1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.

5/16/2015Intelligent Systems and Soft Computing1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.

Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
Neural Networks (II) Simple Learning Rule

Neural Networks (II) Simple Learning Rule
The Perceptron CS/CMPE 333 – Neural Networks. CS/CMPE 333 - Neural Networks (Sp 2002/2003) - Asim LUMS2 The Perceptron – Basics Simplest and one.

The Perceptron CS/CMPE 333 – Neural Networks. CS/CMPE Neural Networks (Sp 2002/2003) - Asim LUMS2 The Perceptron – Basics Simplest and one.
Slide 1 EE3J2 Data Mining EE3J2 Data Mining Lecture 15: Introduction to Artificial Neural Networks Martin Russell.

Slide 1 EE3J2 Data Mining EE3J2 Data Mining Lecture 15: Introduction to Artificial Neural Networks Martin Russell.
An Illustrative Example

An Illustrative Example
Greg GrudicIntro AI1 Introduction to Artificial Intelligence CSCI 3202: The Perceptron Algorithm Greg Grudic.

Greg GrudicIntro AI1 Introduction to Artificial Intelligence CSCI 3202: The Perceptron Algorithm Greg Grudic.
Introduction to Neural Networks John Paxton Montana State University Summer 2003.

Introduction to Neural Networks John Paxton Montana State University Summer 2003.
Neural Networks An Introduction.

Neural Networks An Introduction.
The McCulloch-Pitts Neuron. Characteristics The activation of a McCulloch Pitts neuron is binary. Neurons are connected by directed weighted paths. A.

The McCulloch-Pitts Neuron. Characteristics The activation of a McCulloch Pitts neuron is binary. Neurons are connected by directed weighted paths. A.
COMP305. Part I. Artificial neural networks.. Topic 3. Learning Rules of the Artificial Neural Networks.

COMP305. Part I. Artificial neural networks.. Topic 3. Learning Rules of the Artificial Neural Networks.
Artificial Neural Network

Artificial Neural Network

Similar presentations

Ads by Google