Storage capacity and errors of neural networks

被引：0

作者：

Shubnikov, EI ^{[1
]}

机构：

[1] SI Vavilov State Opt Inst, St Petersburg, Russia

来源：

JOURNAL OF OPTICAL TECHNOLOGY | 2000年 / 67卷 / 02期

关键词：

D O I：

10.1364/JOT.67.000117

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

An estimate of the storage capacity of a neural network working with real images is obtained for neural networks based on correlation optics. It takes into account not only the number of neurons in the network, but also the structure of patterns in the form of the correlation radius of their images. Methods from the theory of statistical solutions and estimation theory are used to determine the errors of the first and second kinds, as well as the error in determining the coordinate of a pattern. The statistical variability of the input pattern, the correlation radius of the image, and the number of neurons and patterns in the memory are taken into account. (C) 2000 The Optical Society of America. [S1070-9762(00)00502-9].

引用

页码：117 / 122

页数：6

共 50 条

[21] Phase diagram and storage capacity of sequence processing neural networks
During, A
Coolen, ACC
Sherrington, D
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1998, 31 (43): : 8607 - 8621
[22] STORAGE CAPACITY OF NEURAL NETWORKS STORING SPATIALLY CORRELATED PATTERNS
SCHLUTER, M
WAGNER, F
PHYSICAL REVIEW E, 1994, 49 (02): : 1690 - 1698
[23] Errors of neural networks
Shubnikov, EI
OPTICS AND SPECTROSCOPY, 2000, 88 (03) : 459 - 465
[24] Errors of neural networks
E. I. Shubnikov
Optics and Spectroscopy, 2000, 88 : 459 - 465
[25] THE SCIENCE OF MAKING ERRORS - WHAT ERROR TOLERANCE IMPLIES FOR CAPACITY IN NEURAL NETWORKS
VENKATESH, SS
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1992, 4 (02) : 135 - 144
[26] HIGH-ORDER NEURAL NETWORKS - INFORMATION-STORAGE WITHOUT ERRORS
PERSONNAZ, L
GUYON, I
DREYFUS, G
EUROPHYSICS LETTERS, 1987, 4 (08): : 863 - 867
[27] LONG-TERM-MEMORY STORAGE CAPACITY OF MULTICONNECTED NEURAL NETWORKS
PERETTO, P
NIEZ, JJ
BIOLOGICAL CYBERNETICS, 1986, 54 (01) : 53 - 63
[28] STORAGE CAPACITY AND LEARNING ALGORITHMS FOR 2-LAYER NEURAL NETWORKS
ENGEL, A
KOHLER, HM
TSCHEPKE, F
VOLLMAYR, H
ZIPPELIUS, A
PHYSICAL REVIEW A, 1992, 45 (10): : 7590 - 7609
[29] Beyond the Maximum Storage Capacity Limit in Hopfield Recurrent Neural Networks
Gosti, Giorgio
Folli, Viola
Leonetti, Marco
Ruocco, Giancarlo
ENTROPY, 2019, 21 (08)
[30] Dynamics and storage capacity of neural networks with small-world topology
Scarpetta, Silvia
De Candia, Antonio
Giacco, Ferdinando
NEURAL NETS WIRN10, 2011, 226 : 218 - 226

← 1 2 3 4 5 →