No Detail Found!

Generalisation performance of mutiplier-free feed forward networks.

Author(s)
Altaf H. Khan Electrical Engineering Department, University of Engineering & Technology, Lahore, Pakistan
Abstract
Feedforward networks with ternary synapses, {-1,0,1}, and unconstrained thresholds can be formed without implementing the floating point multiplier in neurons. The reduced complexity of the neurons, combined with the fact that all synapses are 2-bit deep, makes these networks very attractive for implementation in hardware. Results on the MONK's benchmark, predicting the onset of diabetes, and a hand-written digit recognition task show that these multiplier-free networks are as effective generalisers as conventional continuous-weight feed forward networks.
Publication Details
Page(s) 36-55
DOI DOI not available
Published Journal: New Horizons: Journal of the Institution of Electrical & Electronics Engineers Pakistan, Volume: 37, Issue: , Year: 1999

Request the full text from PASTIC

0

Citations

0

Downloads

36

Views