Noise-robust realization of Turing-complete cellular automata by using neural networks with pattern representation

Makito Oku*, Kazuyuki Aihara

*この論文の責任著者

研究成果: ジャーナルへの寄稿学術論文査読

3 被引用数 (Scopus)

抄録

A modularly-structured neural network model is considered. Each module, which we call a 'cell', consists of two parts: a Hopfield neural network model and a multilayered perceptron. An array of such cells is used to simulate the Rule 110 cellular automaton with high accuracy even when all the units of neural networks are replaced by stochastic binary ones. We also find that noise not only degrades but also facilitates computation if the outputs of multilayered perceptrons are below the threshold required to update the states of the cells, which is a stochastic resonance in computation.

本文言語英語
ページ(範囲)4859-4863
ページ数5
ジャーナルPhysics Letters, Section A: General, Atomic and Solid State Physics
374
48
DOI
出版ステータス出版済み - 2010/11/01

ASJC Scopus 主題領域

  • 物理学および天文学一般

フィンガープリント

「Noise-robust realization of Turing-complete cellular automata by using neural networks with pattern representation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル