This preview shows pages 1–9. 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 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 Feedforward Network Models Feedforward Network Models Feedforward Networks Dynamics Example: Feedforward Networks Dynamics Example: Reaching Reaching Feedforward Networks Feedforward Networks Are the Simplest Kind of Are the Simplest Kind of Brain Circuits Brain Circuits The simplest neuralnetwork model for brain computations is feedforward with one output. The simplest model for the postsynaptic current in a linear feedforward network is d I s d t =  + ( 29 = 1 s d I s d t =  I s + r w r u We assume a steadystate currentto actionpotentialfrequency function (the activation function), F(I s ). An extreme model uses very fast firing: For very slow firing: s d I s d t =  I s + r w r u w ith v = F I s ( ) r d v d t =  v + F I s t ( ) ( ) r d v d t =  v + F r w r u ( ) Neurons can display both slow and fastfiring properties as the mean input current varies. The simplest neuralnetwork model for brain computations is feedforward with one output. A full feedforward network has vector inputs and outputs connected by a weight matrix. For a feedforward network:...
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