Basics of artificial neural network


This video tutorial is the first part of the complete course of deep learning in MATLAB. We recommend you to order the complete course to learn completely.




Artificial Intelligence (AI)

Definition of artificial neural network

Types of artificial neural networks

Applications of artificial neural network

General applications of ANNs

Pattern recognition

Save and review data

Function approximation (nonlinear regression, estimation, and prediction)

Data mining process

Definition of the problem

Data storage

Build a database related to data mining

Select data

Data search

Data conversion (data preparation)

Data exploration

Evaluation of neural network model

Interpret the result of model making and present the results


Biological neurons

Artificial neurons

Mathematical model of a neuron (McClach-Pitts-1943)

Introduction to neural network transfer functions: (hardlim, logsig, hardlims, poslin, purelin, satlins, satlin, tansig, tribas, radbas)

Multilayer neural networks  (MLP)

Sigmoid activation functions

Neural network structure

Training, generalization, and implementation of neural network

Learning in artificial neural networks

Training with the supervisor (Supervised Learning)

Training without an observer (Unsupervised Learning)

Training algorithms

Learn Heb

Delta Learning Law

Competitive learning

Gradient Descent Algorithm


Power of generalization and overfitting

How does the neural network work?

Educational example

Steps of designing a neural network model for classification or prediction (estimation)

Benefits of neural networks

Disadvantages of neural networks

Characteristics of neural networks

A few educational clips

Selection of neural network topology

Network generalizability




Most Artificial Neural Network Architecture

Most Artificial Neural Network Architecture


There are no reviews yet.

Be the first to review “Basics of artificial neural network”

Your email address will not be published. Required fields are marked *