MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS

RIGOROUS BOUNDS.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Summary form only given. The author considers neural networks with N binary neurons and symmetric lth-order synaptic connections, in which m randomly chosen N-bit patterns are stored and retrieved with a small fraction delta of bit errors allowed. The analysis yields rigorous lower bounds for the maximum possible value of l factorial multiplied by alpha , the number of stored bits per distinct synapse: 0. 11 for l equals 2 (compared to 0. 29 as estimated by Hopfield and Amit et al. ), 0. 22 for l equals 3 and 0. 16 for l equals 4.

Original languageEnglish (US)
Title of host publicationUnknown Host Publication Title
PublisherIEEE
Pages50
Number of pages1
StatePublished - 1987

Fingerprint

Neural networks
Data storage equipment
Neurons

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Newman, C. (1987). MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS: RIGOROUS BOUNDS. In Unknown Host Publication Title (pp. 50). IEEE.

MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS : RIGOROUS BOUNDS. / Newman, Charles.

Unknown Host Publication Title. IEEE, 1987. p. 50.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Newman, C 1987, MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS: RIGOROUS BOUNDS. in Unknown Host Publication Title. IEEE, pp. 50.
Newman C. MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS: RIGOROUS BOUNDS. In Unknown Host Publication Title. IEEE. 1987. p. 50
Newman, Charles. / MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS : RIGOROUS BOUNDS. Unknown Host Publication Title. IEEE, 1987. pp. 50
@inproceedings{56bd473f3056437a85490e36dd56cb4b,
title = "MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS: RIGOROUS BOUNDS.",
abstract = "Summary form only given. The author considers neural networks with N binary neurons and symmetric lth-order synaptic connections, in which m randomly chosen N-bit patterns are stored and retrieved with a small fraction delta of bit errors allowed. The analysis yields rigorous lower bounds for the maximum possible value of l factorial multiplied by alpha , the number of stored bits per distinct synapse: 0. 11 for l equals 2 (compared to 0. 29 as estimated by Hopfield and Amit et al. ), 0. 22 for l equals 3 and 0. 16 for l equals 4.",
author = "Charles Newman",
year = "1987",
language = "English (US)",
pages = "50",
booktitle = "Unknown Host Publication Title",
publisher = "IEEE",

}

TY - GEN

T1 - MEMORY CAPACITY IN SYMMETRIC NEURAL NETWORKS

T2 - RIGOROUS BOUNDS.

AU - Newman, Charles

PY - 1987

Y1 - 1987

N2 - Summary form only given. The author considers neural networks with N binary neurons and symmetric lth-order synaptic connections, in which m randomly chosen N-bit patterns are stored and retrieved with a small fraction delta of bit errors allowed. The analysis yields rigorous lower bounds for the maximum possible value of l factorial multiplied by alpha , the number of stored bits per distinct synapse: 0. 11 for l equals 2 (compared to 0. 29 as estimated by Hopfield and Amit et al. ), 0. 22 for l equals 3 and 0. 16 for l equals 4.

AB - Summary form only given. The author considers neural networks with N binary neurons and symmetric lth-order synaptic connections, in which m randomly chosen N-bit patterns are stored and retrieved with a small fraction delta of bit errors allowed. The analysis yields rigorous lower bounds for the maximum possible value of l factorial multiplied by alpha , the number of stored bits per distinct synapse: 0. 11 for l equals 2 (compared to 0. 29 as estimated by Hopfield and Amit et al. ), 0. 22 for l equals 3 and 0. 16 for l equals 4.

UR - http://www.scopus.com/inward/record.url?scp=0023538681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023538681&partnerID=8YFLogxK

M3 - Conference contribution

SP - 50

BT - Unknown Host Publication Title

PB - IEEE

ER -