Real time output derivatives for on chip learning using digital stochastic bit stream neurons
Real time output derivatives for on chip learning using digital stochastic bit stream neurons
In this paper we present the hardware design of an extremely compact and novel digital stochastic neuron, that has the ability to generate the derivative of its output with respect to an arbitrary input. These derivatives may be used to form the basis of an on chip gradient descent learning algorithm.
1775-1777
Daalen, M.
f49a9ae4-bea1-4263-9f23-92835c39fa66
Zhao, J.
5807b9d4-d0e4-4992-a69b-c276636c1691
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
December 1993
Daalen, M.
f49a9ae4-bea1-4263-9f23-92835c39fa66
Zhao, J.
5807b9d4-d0e4-4992-a69b-c276636c1691
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Daalen, M., Zhao, J. and Shawe-Taylor, J.
(1993)
Real time output derivatives for on chip learning using digital stochastic bit stream neurons.
Electronics Letters, 30 (21), .
Abstract
In this paper we present the hardware design of an extremely compact and novel digital stochastic neuron, that has the ability to generate the derivative of its output with respect to an arbitrary input. These derivatives may be used to form the basis of an on chip gradient descent learning algorithm.
Text
RealTimeOutputDerivativesForOnChipLearning.pdf
- Other
More information
Published date: December 1993
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259816
URI: http://eprints.soton.ac.uk/id/eprint/259816
ISSN: 0013-5194
PURE UUID: 88a6d160-0ad9-4db4-8051-91928c193662
Catalogue record
Date deposited: 24 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
M. Daalen
Author:
J. Zhao
Author:
J. Shawe-Taylor
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics