2 March 1994 Modified Maxnet with fast convergence rate
Author Affiliations +
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.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Orly Yadid-Pecht, Moshe Gur, "Modified Maxnet with fast convergence rate", Proc. SPIE 2243, Applications of Artificial Neural Networks V, (2 March 1994); doi: 10.1117/12.169957; https://doi.org/10.1117/12.169957
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Beta-CMOS implementation of an artificial neuron
Proceedings of SPIE (March 22 1999)
High-speed low-power analog ASICs for a 3D neuroprocessor
Proceedings of SPIE (March 28 1995)
Machine vision applications of analog neural net chips
Proceedings of SPIE (September 16 1992)
Stereodisplay with neural network image processing
Proceedings of SPIE (June 28 2001)
Learning in linear feature-discovery networks
Proceedings of SPIE (December 01 1991)
Very-low-noise switching-free CNN-based adder
Proceedings of SPIE (November 02 1999)

Back to Top