ON THE GENERALIZATION ABILITY OF DILUTED PERCEPTRONS

被引：11

作者：

KUHLMANN, P ^{[1
]}

MULLER, KR ^{[1
]}

机构：

[1] TECH UNIV BERLIN 1,GMD FORSCHUNGSINST RECHNERARCHITEKUTUR & SOFTWARETECH,D-12489 BERLIN,GERMANY

来源：

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1994年 / 27卷 / 11期

关键词：

D O I：

10.1088/0305-4470/27/11/026

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

A linearly separable Boolean function is learned by a diluted perceptron with optimal stability. A different level of dilution is allowed for teacher and student perceptron. The learning algorithms used were the optimal annealed dilution and Hebbian dilution. The generalization ability, i.e. the probability to recognize a pattern which has not been learned before, is calculated in replica symmetry.

引用

页码：3759 / 3774

页数：16

共 50 条

[21] On the generalization ability of recurrent networks
Hammer, B
ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS, 2001, 2130 : 731 - 736
[22] On the Generalization Ability of GRLVQ Networks
Barbara Hammer
Marc Strickert
Thomas Villmann
Neural Processing Letters, 2005, 21 : 109 - 120
[23] On the generalization ability of GRLVQ networks
Hammer, B
Strickert, M
Villmann, T
NEURAL PROCESSING LETTERS, 2005, 21 (02) : 109 - 120
[24] Convergence and generalization ability of CMAC
He, Chao
Xu, Li-Xin
Zhang, Yu-He
Kongzhi yu Juece/Control and Decision, 2001, 16 (05): : 523 - 529
[25] Generalization ability of folding networks
Hammer, B
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2001, 13 (02) : 196 - 206
[26] On the Generalization Ability of Unsupervised Pretraining
Deng, Yuyang
Hong, Junyuan
Zhou, Jiayu
Mandavi, Mehrdad
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
[27] A novel training scheme for multilayered perceptrons to realize proper generalization and incremental learning
Chakraborty, D
Pal, NR
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (01): : 1 - 14
[28] Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise
Schottky, B
Krey, U
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1997, 30 (24): : 8541 - 8571
[29] A Kuhn-Tancker cavity method for generalization with applications to perceptrons with Ising and Potts neurons
Gerl, F
Krey, U
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1995, 28 (23): : 6501 - 6516
[30] GENERALIZATION ABILITY OF MOS PREDICTION NETWORKS
Cooper, Erica
Huang, Wen-Chin
Toda, Tomoki
Yamagishi, Junichi
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 8442 - 8446

← 1 2 3 4 5 →