4_16_09_EnergyMinimization_1

4_16_09_EnergyMinimization_1 - Swimming uses half centers,...

Info iconThis preview shows pages 1–13. Sign up to view the full content.

View Full Document Right Arrow Icon
Background image of page 1

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

View Full DocumentRight Arrow Icon
Background image of page 2
Swimming uses half centers, with cross inhibition ending mainly by local inhibition.
Background image of page 3

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

View Full DocumentRight Arrow Icon
The bifurcation diagram shows fixed points and limit cycles of varying frequencies as one modulates the tonic excitation to C neurons).
Background image of page 4
David Marr’s three levels of understanding computations.
Background image of page 5

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

View Full DocumentRight Arrow Icon
To understand the computation of a neural network, consider a simple feedforward case.
Background image of page 6
A network like this is a resistive network, which, in steady state, minimizes electrical energy.
Background image of page 7

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

View Full DocumentRight Arrow Icon
Computations performed by neural networks can be expressed as energy minimization.
Background image of page 8
The advantage to do so is emphasizing the computational strategy not the implementation.
Background image of page 9

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

View Full DocumentRight Arrow Icon
Example: Aperture problem: small receptive fields can only measure components of velocity parallel to luminance gradients.
Background image of page 10
The variables of the aperture problem are the components of velocity parallel ( V (s)) and perpendicular ( V (s)) to the moving contour.
Background image of page 11

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

View Full DocumentRight Arrow Icon
V s ( ) = v T s ( ) T s ( ) + v s ( ) N s ( ) The true velocity at each position of the contour obeys However, we can only measure N (s) and V .
Background image of page 12
Image of page 13
This is the end of the preview. Sign up to access the rest of the 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 / 22

4_16_09_EnergyMinimization_1 - Swimming uses half centers,...

This preview shows document pages 1 - 13. Sign up to view the full document.

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