Neural Networks for Applied Sciences and Engineering--Chapter 2

Chapter 2 Fundamentals of Neural Networks and Models for Linear Data Analysis

The full article：http://note.youdao.com/noteshare?id=909ec7e9da92bccc62de17a2feb04a40

2.5 Neuron Models and Learning Strategies

2.5.1 Threshold Neuron as a Simple Classifier

2.5.2 Learning Models for Neurons and Neural Assemblies

2.5.2.1 Hebbian Learning

Maybe Hebbian Learning is better to do unsupervised or competitive learning!?

2.5.3 Perceptron with Supervised Learning as a Classifier

2.5.3.1 Perceptron Learning Algorithm

It could demonstrate the new omiga can make the new u approach to the true value than the old.For example:

2.5.4 Linear Neuron for Linear Classification and Prediction

2.5.4.1 Learning with the Delta Rule

example-by-example learning versus batch learning

2.5.4.9 Multiple Linear Neuron Models

because Multiple Linear Neuron Models adjusts weights by cost function which is related to all yi, it studies the simultaneous effect on several dependent variables.