A single-iteration threshold Hamming network

We analyze in detail the performance of a Hamming network classifying inputs that are distorted versions of one of its m stored memory patterns, each being a binary vector of length n. It is shown that the activation function of the memory neurons in the original Hamming network may be replaced by a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks 1995-01, Vol.6 (1), p.261-266
Main Authors: Meilijson, I., Ruppin, E., Sipper, M.
Format: Article
Language:English
Subjects:
Access methods and protocols, osi model
Applied sciences
Artificial intelligence
Computer networks
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Hamming distance
Logic functions
Network topology
Neurons
Pattern analysis
Performance analysis
Telecommunications
Telecommunications and information theory
Teleprocessing networks. Isdn
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:We analyze in detail the performance of a Hamming network classifying inputs that are distorted versions of one of its m stored memory patterns, each being a binary vector of length n. It is shown that the activation function of the memory neurons in the original Hamming network may be replaced by a simple threshold function. By judiciously determining the threshold value, the "winner-take-all" subnet of the Hamming network (known to be the essential factor determining the time complexity of the network's computation) may be altogether discarded. For m growing exponentially in n, the resulting threshold Hamming network correctly classifies the input pattern in a single iteration, with probability approaching 1.< >
ISSN:1045-9227
1941-0093
DOI:10.1109/72.363428