Abstract
A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented.
Original language | English |
---|---|
Pages (from-to) | 111-118 |
Number of pages | 8 |
Journal | Proceedings of SPIE - The International Society for Optical Engineering |
Volume | 2243 |
DOIs | |
State | Published - 2 Mar 1994 |
Externally published | Yes |
Event | Applications of Artificial Neural Networks V 1994 - Orlando, United States Duration: 4 Apr 1994 → 8 Apr 1994 |
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering