Neural A/D with Resolution Enhancement
by Jody Drake and Dave Comisky Advisor: Dr. Gary Dempsey Man is separated from machines by the ability to think reason, imagine
and create. All of these actions are made possible via a complex network
of neurons, massed at the top of the brain stem. Artificial neural networks
attempt to simulate the actions of these biological neurons. Like their
biological counterparts, network feedback produces trained outputs for
given inputs, that is, the system learns. Neural control has significant
advantages in analog to digital conversion. During the course of this project,
we have researched traditional neural schemes and developed a new line
of attack for a 4 bit neural A/D converter. This converter offers significant
advantages over traditional A/D in cost, speed and accuracy. Preliminary
testing has shown an increase to 8 bit accuracy with a conversion time
less than 90 microseconds.
|
[Prospective Students]
[Current Students]
[Alumni]
[Faculty]
[Home] [Contact us] [Curriculum] [Senior Projects] [Research] [People] [Links] Copyright (c)1995-2013 Bradley University. All rights reserved. . . |