chapter2 - Chapter 2 Learning Chapter 2 Learning 2 Basic...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Chapter 2 Learning Chapter 2 --- Learning 2 Basic Concepts s Learning is a process by which the free parameters of a neural network are adapted through a continuing process of stimulation by the environment in which the network is embedded. s In ANN, learning is the modifications of the associated weight of the interconnections according to some rules. Chapter 2 --- Learning 3 Basic Concepts Learning = Build up Memory, and Memory = Interconnection Weights Learning = Adjust the Weights . New weight = Old weight + Change in weight w ji ( n +1) = w ji ( n ) + Δ w ji ( n ) Chapter 2 --- Learning 4 Learning Process 1. The NN is stimulated by an environment. 2. The NN undergoes changes as a result of this stimulation. 3. The NN responds in a new way to the environment because of the changes that have occurred in its internal structure. Chapter 2 --- Learning 5 3 Types of Learning 1. Unsupervised Learning s Hebbian Learning s Competitive Learning 2. Supervised Learning s Error-Correction Learning 3. Reinforcement Learning Chapter 2 --- Learning 6 Hebbian Learning s A kind of unsupervised learning, only involves local interaction between neurons, with no global teacher. s A synapse connecting two neurons is strengthened whenever both of those neurons fire. s Strengthening a synapse according to the correlation between the excitation levels of the neurons that it connects. Chapter 2 --- Learning 7 Hebbian Learning Input Layer Output Layer Hidden Layer Local Learning Local Learning Independent Chapter 2 --- Learning 8 Signal Hebbian Learning s Activity product rule : the weight change is proportional to the product of the incoming and outcoming signal of the neurons....
View Full Document

This note was uploaded on 04/13/2011 for the course EE 4210 taught by Professor Wong during the Spring '10 term at City University of Hong Kong.

Page1 / 25

chapter2 - Chapter 2 Learning Chapter 2 Learning 2 Basic...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online