This preview shows pages 1–7. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Outline of the Lecture Outline of the Lecture Linear Recurrent Network Models Linear Recurrent Network Models Recurrent Matrices Eigenvalues, Eigenvectors Recurrent Matrices Eigenvalues, Eigenvectors Properties Properties SynapticMatrix Eigenvector SynapticMatrix Eigenvector Properties Determine Properties Determine Responses of Linear Responses of Linear Recurrent Networks Recurrent Networks A full feedforward network has vector inputs and outputs connected by a weight matrix. A recurrent network is a feedforward network with a recurrent synaptic weight matrix. For a feedforward network: For a recurrent network: τ r d v a d t =  v a + F W a b b = 1 N a å u b ae è ç ö ø ÷ ae è ç ö ø ÷ τ r d r v d t =  r v + F W × r u ( ) τ r d r v d t =  r v + F W × r u + M × r v ( ) Assuming that the activation function F is linear, that is, F(x)=x, and denoting the input as h =...
View
Full
Document
This note was uploaded on 06/08/2009 for the course BME 575L taught by Professor Grzywacz during the Spring '09 term at USC.
 Spring '09
 Grzywacz

Click to edit the document details