Investigation of Decreasing the Convergence Time of a Modified
Hopfield Neuron
by Michael A. Waldschmidt Advisor: Dr. Gary Dempsey In this project options that will decrease the convergence time of the
Hopfield neuron are investigated. This neuron will be used in a parallel
processing architecture which uses feedback to share information between
neurons. Example applications are a neural image processing system using
the Hough Transform algorithm and a neural analog-to-digital converter.
The intensive simulation required to check and justify four new ideas and
approaches are reviewed. Two neurons were implemented in hardware to verify
simulation results.
|
[Prospective Students]
[Current Students]
[Alumni]
[Faculty]
[Home] [Contact us] [Curriculum] [Senior Projects] [Research] [People] [Links] Copyright (c)1995-2013 Bradley University. All rights reserved. . . |