By Kardi Teknomo, PhD .

NN

Share this: Google+
| Next >

Neural Network Tutorial

We will start with the basic simplest neuron model, and then we will develop it into more and more complex network architecture. Depending on the network architecture, the non-linear function inside the neuron and the learning methods and its purposes, different name of neural network models was developed. However, in this tutorial we will discuss the most famous feedforward network such as McCulloch and Pit, Perceptron, ADaptive LInear Neuron (ADALINE), Multi-Layer Perceptron (MLP), Many ADaptive LInear Neuron (MADALINE) and Back Propagation Network.

Through the work numerical examples, you will learn step by step how to use the existing neural network and then how to build your own neural network that can learn from examples using mere spreadsheet of Microsoft Excel, without macro programming. Indeed, this is unique tutorial is useful for people who want to learn neural network in a very fast way. The spreadsheets companion of this tutorial are available for download only for those who purchase the full version of this tutorial.

The author assumes the readers have no prior knowledge on data science or neural network. The mathematics level has been pulled down to a high school level or into the beginning of college level. There is no need to understand calculus deeply and there is no programming is necessary. However, the author also assumes the readers know how to write formulas and how to use spreadsheet in Microsoft Excel. This is not Excel tutorial for beginners. In fact, after learning this book, you will appreciate how to use the spreadsheet in more powerful ways.

More than 50 numerical examples and more than 10 spreadsheet solutions are provided in this tutorial. The examples are given in boxes to represent the steps you need to master before going further. Exercises at the end of each section are very useful to explore the variation of values.

Topics of this tutorial are:

  1. What is Neural Network?
    1. Why Use Neural Network?
    2. Limitation of Neural Network
    3. Neural Network Terminologies and Notations
  2. Model of a Neuron
    1. Aggregation Function
    2. Activation Function
    3. Bias and Dummy Input
  3. Boolean Logic using Single Layer Neural Network
  4. Input-Output Diagram of Perceptron
  5. Building Neural Network using Spreadsheet
  6. Training Single Layer Neural Network
  7. Advanced Training Single Layer Neural Network using Spreadsheet
  8. Single Layer Bipolar Neural Network
  9. Multi-Layer Neural Network
  10. Training Neural Network using Back Propagation
    1. Problems with Back Propagation
  11. Training Neural Network Using Excel Solver
  12. Plug & Play Neural Network
    1. Boolean Neural Network
    2. Arithmetic Neural Network
  13. Neural Network for Regression Analysis
    1. Simple Linear Regression
    2. Multiple Linear Regression
    3. Logistic Regression
    4. Polynomial Regression
  14. Applications of Neural Network
    1. Design of Neural Network
    2. Training Neural Network
    3. Neural Network Utilization
  15. Classification Application: Prediction Beyond Expert System
  16. Image Processing Application: Optical Number Recognition
  17. Forecasting from Time Series Data
  18. Summary: Integrated Approach to Neural Network

Read it off line on any device. Click here to purchase the complete E-book of this tutorial

See Also :
K means clustering , Similarity Measurement , Reinforcement Learning (Q-Learning) , Discriminant Analysis , Kernel Regression , Clustering , Decision Tree, Practice Neural Network in Python

This tutorial is copyrighted .

Preferable reference for this tutorial is

Teknomo, Kardi (2017). Neural NetworkTutorial. http:\\people.revoledu.com\kardi\tutorial\NeuralNetwork\