STATISTICAL-MECHANICS OF UNSUPERVISED LEARNING

被引：28

作者：

BIEHL, M

MIETZNER, A

机构：

[1] Physikalisches Institut, Julius-Maximilians-Universität, Würzburg, D-9707h, Am Hubland

来源：

EUROPHYSICS LETTERS | 1993年 / 24卷 / 05期

关键词：

D O I：

10.1209/0295-5075/24/5/017

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

We study two different unsupervised learning strategies for a single-layer perceptron. The environment provides a set of unclassified training examples, which belong to two different classes, depending on their overlap with an N-dimensional concept vector. By means of a statistical-mechanics analysis, using the replica method, we investigate how well the perceptron infers the unknown structure from the input data.

引用

页码：421 / 426

页数：6

共 20 条

[11]

MIETZNER A, UNPUB

[12]

Minsky M., 1969, PERCEPTRONS

[13]

Minsky ML, 1988, PERCEPTRONS

[14] A SIMPLIFIED NEURON MODEL AS A PRINCIPAL COMPONENT ANALYZER [J].

OJA, E .

JOURNAL OF MATHEMATICAL BIOLOGY, 1982, 15 (03) :267-273

[15] ON THE ABILITY OF THE OPTIMAL PERCEPTRON TO GENERALIZE [J].

OPPER, M ;

KINZEL, W ;

KLEINZ, J ;

NEHL, R .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1990, 23 (11) :L581-L586

[16]

Rosenblatt F, 1962, PRINCIPLES NEURODYNA

[17]

RUJAN P, 1992, PREPRINT U OLDENBURG

[18] FAST RECOGNITION OF REAL OBJECTS BY AN OPTIMIZED HETERO-ASSOCIATIVE NEURAL NETWORK [J].

SCHMITZ, HJ ;

POPPEL, G ;

WUNSCH, F ;

KREY, U .

JOURNAL DE PHYSIQUE, 1990, 51 (02) :167-183

[19] STATISTICAL-MECHANICS OF LEARNING FROM EXAMPLES [J].

SEUNG, HS ;

SOMPOLINSKY, H ;

TISHBY, N .

PHYSICAL REVIEW A, 1992, 45 (08) :6056-6091

[20] THE STATISTICAL-MECHANICS OF LEARNING A RULE [J].

WATKIN, TLH ;

RAU, A ;

BIEHL, M .

REVIEWS OF MODERN PHYSICS, 1993, 65 (02) :499-556

← 1 2 →