Optical implementation of the Kak neural network

Authors:
A. Shortt;J. G. Keating;L. Moulinier;C. N. Pannell
Affiliations:
Department of Computer Science, National University of Ireland, Maynooth, Maynooth, Co. Kildare, Ireland;Department of Computer Science, National University of Ireland, Maynooth, Maynooth, Co. Kildare, Ireland;Building of Physical Sciences (Room 116), University of Kent, Canterbury, CT2 7NR, UK;Building of Physical Sciences (Room 116), University of Kent, Canterbury, CT2 7NR, UK
Venue:
Information Sciences—Informatics and Computer Science: An International Journal
Year:
2005

Citing 5
Cited 3

New algorithms for training feedforward neural networks

Pattern Recognition Letters
Two corner classification algorithms for training the Kak feedforward neural network

Information Sciences—Intelligent Systems: An International Journal
Comparison of learning and generalization capabilities of the Kak and the backpropagation algorithms

Information Sciences—Intelligent Systems: An International Journal
On generalization by neural networks

Information Sciences—Informatics and Computer Science: An International Journal
A neural network-based intelligent metasearch engine

Information Sciences—Informatics and Computer Science: An International Journal

Computational intelligence in photonics technology and optical networks: A survey and future perspectives

Information Sciences: an International Journal
A neural network based on the generalized Fischer-Burmeister function for nonlinear complementarity problems

Information Sciences: an International Journal
Artificial neural networks in hardware: A survey of two decades of progress

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show that the Kak neural network is suitable for optical implementation using a bipolar matrix vector multiplier. We demonstrate how the CC4 algorithm, with suitable modifications to the structure and training algorithm, may be used to build an optical neural network implementing N-Parity.