Development
Data Science
Neural Networks
Artificial Neural Networks tutorial - theory & applications
4.1 (24 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
110 students enrolled

Artificial Neural Networks tutorial - theory & applications

Machine learning algorithm (ANN) - simplified. See the use cases with R to understand the application
4.1 (24 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
110 students enrolled
Created by Gopal Prasad Malakar
Last updated 8/2017
English
English
Preview this course
Artificial Neural Networks tutorial - theory & applications
Current price: $13.99 Original price: $19.99 Discount: 30% off
5 hours left at this price!
Buy now
30-Day Money-Back Guarantee
This course includes
  • 1 hour on-demand video
  • 6 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
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
Expand all 13 lectures 01:09:37
+ – Introduction to Neural Network
6 lectures 32:15
What will you learn in this course?
Preview 01:15
How to study this course?
01:23
Inspiration and linkage with animal thinking process
What is neural network? Motivation behind neural network
07:03
  • What is node
  • What is bias
  • What is hidden layer / input layer / output layer
  • What is activation function
  • What is a feed forward model
Terms Associated with Neural Network
07:12

Understand

  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?
How does a Neural Network algorithm work?
Preview 09:58
High level discussion on how to pre process the data for neural network
Data Preprocessing required to apply ANN
05:24
+ – Application of Neural Network using R
7 lectures 37:22

Can it predict outcome - when dependent variable has two possible outcome?

Demo of neural network application on cheese data - can it predict the outcome?
07:57

Can it predict outcome - when dependent variable has more than two possible outcome?

Demo of neural network application on multi class dependent variable?
11:42
Pros n Cons of Neural Network Models
03:57
Check your learning of ANN
10 questions
About assignment - solve a binary outcome case using ANN
Preview 01:30
Assignment tasks
02:03
Sample solution of assignment
08:43
Closing Note
01:30
Requirements
  • Should know basic R programming
  • Basic computer skills
  • Ability to locate resource supplied with this course on Udemy platform
Description

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
Who this course is for:
  • Analytics professionals, who are trying to learn artificial neural network
  • Students, who are trying to make their career into analytics domain
  • Finance professionals, who want to get first hand exposure of artificial neural network concepts