COMPLETE SOLUTION OF THE LOCAL MINIMA IN THE XOR PROBLEM

被引：23

作者：

LISBOA, PJG

PERANTONIS, SJ

机构：

[1] UNIV LIVERPOOL,DEPT ELECT ENGN & ELECTR,LIVERPOOL L69 3BX,ENGLAND

[2] UNIV LIVERPOOL,DEPT APPL MATH & THEORET PHYS,LIVERPOOL L69 3BX,ENGLAND

[3] UNIV LIVERPOOL,DEPT COMP SCI,LIVERPOOL L69 3BX,ENGLAND

来源：

NETWORK-COMPUTATION IN NEURAL SYSTEMS | 1991年 / 2卷 / 01期

关键词：

D O I：

10.1088/0954-898X/2/1/007

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A complete solution of the excitation values which may occur at the local minima of the XOR problem is obtained analytically for two-layered networks in the two most commonly quoted configurations, using the gradient backpropagation algorithm. The role of direct connections which bypass the two-layered system is discussed in connection to the XOR problem and other related training tasks.

引用

页码：119 / 124

页数：6

共 5 条

[1] CONVERGENCE OF RECURSIVE ASSOCIATIVE MEMORIES OBTAINED USING THE MULTILAYERED PERCEPTRON [J].

LISBOA, PJG ;

PERANTONIS, SJ .

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1990, 23 (17) :4039-4053

[2]

Minsky ML, 1969, PERCEPTRONS

[3]

Rumelhart David E., 1987, LEARNING INTERNAL RE, P318

[4] LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS [J].

RUMELHART, DE ;

HINTON, GE ;

WILLIAMS, RJ .

NATURE, 1986, 323 (6088) :533-536

[5]

WALLACE DJ, 1987, COMPUTATIONAL PHYSIC, P168

← 1 →