Binary Second-Order Recurrent Neural Networks for Inferring Regular Grammars

スポンサーリンク

概要

• 論文の詳細を見る

• This paper proposes the binary second-order recurrent neural networks (BSRNN) equivalent to the modified finite automata (MFA) and presents the learning algorithm to construct the stable BSRNN for inferring regular grammar. This network combines two trends; one is to transform strings of a regular grammar into a recurrent neural network through training with no restriction of the number of neurons, the number of strings, and the length of string and the other is to directly transform itself into a finite automation. Since neurons in the BSRNN employ a hard-limiter activation functions, the proposed BSRNN can become a good alternative of hardware implementation for regular grammars and finite automata as well as grammatical inference.

• 社団法人電子情報通信学会の論文
• 2000-11-25

著者

• Yoon Hyunsoo

  The Authors Are With The Eecs Kaist

• Yoon Hyunsoo

  The Author Is With The Department Of Computer Science Korea Advanced Institute Of Science And Techno

• Jung Soon-ho

  The Author Is With The Division Of Electronics Computer Information Communication Engineering Pukyon

関連論文

• Adaptive TCP Receiver Window Control on Channel Conditions for Wireless Systems(Special Issue on Parallel and Distributed Computing, Applications and technologies)
• Adaptive Backtracking Handover Scheme Using a Best-Fit COS Search Method for Improving Handover Efficiency in Wireless ATM Networks(Special Issue on Parallel and Distributed Computing, Applications and technologies)
• Binary Second-Order Recurrent Neural Networks for Inferring Regular Grammars

スポンサーリンク