2_24_09_NonlinearRecurrentNetworks

2_24_09_NonlinearRecurrentNetworks - Outline of the Lecture...

Info iconThis preview shows pages 1–7. 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
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Outline of the Lecture Outline of the Lecture Nonlinear Recurrent Network Models Nonlinear Recurrent Network Models Rectification Winner-take-all Gain Rectification Winner-take-all Gain Modulation Modulation Rectification Induces Higher Rectification Induces Higher Amplification and Selection, Amplification and Selection, and Tuning and Gain and Tuning and Gain Controls Controls A recurrent network is a feedforward network with a recurrent synaptic weight matrix. Assuming that the activation function F is linear, that is, F(x)=x, and denoting the input as h = W . u r d v d t = - v + h + M v r d v d t = - I v + h + M v r d v d t = M- I ( ) v + h r d v d t = - v + F W u + M v ( ) We now consider the consequences of the assumption that the activation function is a rectification with threshold : F r h + ( 29 = + - + r x [ ] + = 0 0 < 0 r We also consider the continuous approximation for recurrent networks (for the particular example of orientation selectivity):...
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.

Page1 / 25

2_24_09_NonlinearRecurrentNetworks - Outline of the Lecture...

This preview shows document pages 1 - 7. Sign up to view the full document.

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