Engineering Artificial Neuronal Systems
Presented on 8/22/98 at the UW/MSR
Summer Workshop on Intelligent Systems
Click here to start
Table of Contents
Engineering Artificial Neuronal Systems
Both of these machines compute...
Computation and biology
Consider a hypothetical problem...
The answer is yes...
Transistors exhibit gain and nonlinearity
Gain & nonlinearity ? switching and restoration
Switching enables mathematics
Mathematics affords computation
Paradigms underlying digital computation
The cost of an impoverished representation
Why might we need a new approach?
We can learn from neurobiology
Do simple paradigms underlie neuronal computation?
Is adaptation a fundamental paradigm?
We can build adaptive silicon systems
Silicon learning can emulate neurobiology
Silicon signaling can emulate neurobiology
An open question...
Author:
Chris Diorio
Email:
diorio@cs.washington.edu
Home Page:
http://www.cs.washington.edu/people/faculty/diorio/