识别作为米利-摩尔机的局部反馈递归网络的特定局限性。

Identification of a specific limitation on local-feedback recurrent networks acting as Mealy-Moore machines.

作者信息

Kremer S C

机构信息

Guelph Natural Computation Research Group, Computing and Information Science Department, University of Guelph, Guelph, Ontario, N1G 2W1, Canada.

出版信息

IEEE Trans Neural Netw. 1999;10(2):433-8. doi: 10.1109/72.750574.

DOI:10.1109/72.750574

PMID:18252541

Abstract

This paper describes a proof which identifies limitations of local-feedback recurrent networks (LFRN's) in representing Mealy-Moore machines. Specifically, it identifies a class of machines that are unrepresentable in these networks. While it is known that LFRN's cannot represent all automata, this is the first paper to show a specific class of unrepresentable automata. The paper goes beyond previous work in the area by addressing realistic activation functions, arbitrary network architectures, and more general computing machines.

摘要

本文描述了一种证明，该证明确定了局部反馈递归网络（LFRN）在表示米利-摩尔机方面的局限性。具体而言，它确定了一类在这些网络中无法表示的机器。虽然已知LFRN无法表示所有自动机，但这是第一篇展示特定类不可表示自动机的论文。本文通过探讨实际的激活函数、任意的网络架构和更通用的计算机器，超越了该领域以前的工作。