paper available: Practical Performance and Credit Assignment...

[Marwan Jabri]

FTP-host: archive.cis.ohio-state.edu
FTP-filename: /pub/neuroprose/jabri.ppap.ps.Z

The file jabri.ppap.ps.Z is now available for
copying from the Neuroprose repository and has been 
submitted for publication:


	Practical Performance and Credit Assignment Efficiency 
	of Analog Multi-layer Perceptron Perturbation Based 
	Training Algorithms

	Marwan A. Jabri

	Systems Engineering and Design Automation Laboratory 
	Sydney University Electrical Engineering
	NSW 2006 Australia
	marwan at sedal.su.oz.au

	SEDAL Technical Report 1-7-94


Abstract
Many algorithms have been recently reported for the training of analog
multi-layer perceptron. Most of these algorithms were evaluated either
from a computational or simulation view point. This paper applies several
of these algorithms to the training of an analog multi-layer perceptron
chip. The advantages and shortcomings of these algorithms in terms of
training and generalisation performance and their capabilities in a
limited precision environment are discussed. Extensive experiments
demonstrate that a trade-off exists between the parallelisation of
perturbations and the efficiency of credit assignment. Two
semi-parallelisation heuristics are presented and are shown to provide
advantages in terms of efficient exploration of the solution space and
fewer credit assignment confusions.


Retrieve this paper by anonymous ftp from:
archive.cis.ohio-state.edu (128.146.8.52)
    in the /pub/neuroprose    directory

The name of the paper in this archive is:
    jabri.ppap.ps.Z          [28 pages]


Sorry, but no hard copies available.