Theory of Minimizing Linear Separation Automata

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we theoretically analyze a certain extension of a finite automaton, called a linear separation automaton (LSA). An LSA accepts a sequence of real vectors, and has a weight function and a threshold sequence at every state, which determine the transition from some state to another at each step. Transitions of LSAs are just corresponding to the behavior of perceptrons. We develop the theory of minimizing LSAs by using Myhill-Nerode theorem for LSAs. Its proof is performed as in the proof of the theorem for finite automata. Therefore we find that the extension to an LSA from the original finite automaton is theoretically natural.

• 一般社団法人情報処理学会の論文
• 2010-03-17

著者

• Satoshi Kobayashi

  Department Of Computer Science Graduate School Of Electro-communications The University Of Electro-c

• Yuji Numai

  Department Of Computer Science Graduate School Of Electro-communications The University Of Electro-c

• Yoshiaki Udagawa

  NTT-IT Corporation

• Satoshi Kobayashi

  Department of Anatomy, Sinshu University School of Medicine

関連論文

• State and Threshold Sequence Minimization Algorithm of Linear Separation Automata
• Theory of Minimizing Linear Separation Automata
• The Usefulness and Limitations of Intravenous Digital Sub-tractionAngiography Screening in Detecting Unrup-tured Cerebral Aneurysmsand Methods to Improve its Reliability

スポンサーリンク