Perfect Fault Tolerance of the n-k-n Network

It was shown in Phatak, Choi, and Koren (1993) that the neural network implementation of the encoder-decoder has a minimal size of = 2, and it was shown how to construct the network. A proof was given in Phatak and Koren (1995) that in order to achieve perfect fault tolerance by replicating the hidd...

Full description

Saved in:
Bibliographic Details
Published in:Neural computation 2005-09, Vol.17 (9), p.1911-1920
Main Authors: Tchernev, Elko B., Mulvaney, Rory G., Phatak, Dhananjay S.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Exact sciences and technology
Learning and adaptive systems
Mathematics
Miscellaneous
Neural networks
Neural Networks (Computer)
Probability and statistics
Probability theory and stochastic processes
Proof theory
Sciences and techniques of general use
Special processes (renewal theory, markov renewal processes, semi-markov processes, statistical mechanics type models, applications)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It was shown in Phatak, Choi, and Koren (1993) that the neural network implementation of the encoder-decoder has a minimal size of = 2, and it was shown how to construct the network. A proof was given in Phatak and Koren (1995) that in order to achieve perfect fault tolerance by replicating the hidden layer, the required number of replications is at least three. In this note, exact lower bounds are derived for the number of replications as a function of , for the network and for the log network.
ISSN:0899-7667
1530-888X
DOI:10.1162/0899766054322946