Artificial Neural Networks tutorial – theory & applications

Machine learning algorithm (ANN) – simplified. See the use cases with R to understand the application

This course aims to simplify concepts of Artificial Neural Network (ANN). ANN mimics the process of thinking. Using it’s inherent structure, ANN can solve multitude of problem like binary classifications problem, multi level classification problem etc.

What you’ll learn

  • Basics of Artificial Neural Network (ANN).
  • Terms and defintions associated with ANN.
  • How does ANN work.
  • How to solve binary classification problem using artificial neural network in R.
  • How to solve multi level classification problem using artificial neural network in R.
  • Data treatment guideline for using ANN.
  • Pros and Cons of Neural Network.

Course Content

  • Introduction to Neural Network –> 6 lectures • 32min.
  • Application of Neural Network using R –> 7 lectures • 37min.

Artificial Neural Networks tutorial - theory & applications

Requirements

  • Should know basic R programming.
  • Basic computer skills.
  • Ability to locate resource supplied with this course on Udemy platform.

This course aims to simplify concepts of Artificial Neural Network (ANN). ANN mimics the process of thinking. Using it’s inherent structure, ANN can solve multitude of problem like binary classifications problem, multi level classification problem etc.

The course is unique in terms of simplicity and it’s step by step approach of presenting the concepts and application of neural network.

The course has two section

——————————————————-

Section 1 : Theory of artificial neural network

——————————————————–

  1. what is neural network
  2. Terms associated with neural network
    1. What is node
    2. What is bias
    3. What is hidden layer / input layer / output layer
    4. What is activation function
    5. What is a feed forward model
  3. How does a Neural Network algorithm work?
    1. What is case / batch updating
    2. What is weight and bias updation
    3. Intuitive understanding of functioning of neural network
    4. Stopping criteria
    5. What decisions an analyst need to take to optimize the neural network?
  4. Data Pre processing required to apply ANN

——————————————————-

Section 2 : Application of artificial neural network

——————————————————–

  1. Application of ANN for binary outcome
  2. Application of ANN for multi level outcome
  3. Assignment of ANN – learn by doing