Artificial Neural Networks

Course

Artificial Intelligence

Course Code

Comp 412

Lecturer

Mr. Kebut

Contents

Artificial neural networks 2

Advantages: 2

Disadvantages: 3

The Biological Model 5

The Mathematical Model 7

A framework for distributed representation 8

Processing units 9

Neural Network topologies 10

Training of artificial neural networks 11

Natural language processing 12

Types of communicating agents 15

1 Agents that share a common internal communication language 15

2 Agents that make no assumption about each other’s internal language 15

2.1 Defining the language (subset of English) 16

Grammar 17

2.2 Syntactic analysis 18

Depth First parsing 19

Breadth First parsing 20

Definite Clause Grammars (DCG) 20

 Augmenting the DCG 21

 Verify grammatical correct sentences 22

 Augment the DCG with a new parameter to describe the case 24

 Augment the DCG with a new parameter to describe the verb subcategorization 24

Resulting augmented DCG 26

2.3 Semantic analysis 27

Augment DCG with semantic interpretation 27

2.4 Pragmatic interpretation 28

2.5 Ambiguity 29

Introduction to Robotics 31

2 Design of industrial robots 32

(a) Dynamic system 34

Reasoning Under Uncertainty 40

Artificial neural networks

An artificial neural network is a system based on the operation of biological neural networks, in other words, is an emulation of biological neural system. Why would be necessary the implementation of artificial neural networks? Although computing these days is truly advanced, there are certain tasks that a program made for a common microprocessor is unable to perform; even so a software implementation of a neural network can be made with their advantages and disadvantages.

Advantages:

* A neural network can perform tasks that a linear program can not.

* When an element of the neural network fails, it can continue without any problem by their parallel nature.

* A neural network learns and does not...