Singular-value-decomposition analysis of associative memory in a neural network

Tatsuya Kumamoto, Mao Suzuki, Hiroaki Matsueda

研究成果: Article査読

5 被引用数 (Scopus)

抄録

We evaluate performance of associative memory in a neural network by based on the singular value decomposition (SVD) of image data stored in the network. We consider the situation in which the original image and its highly coarse-grained one by SVD are stored in the network and the intermediate one is taken as an input. We find that the performance is characterized by the snapshot-entropy scaling inherent in the SVD: the network retrieves the original image when the entropy of the input image is larger than the critical value determined from the scaling. The result indicates efficiency of the SVD as a criterion of the performance and also indicates universality of the scaling for realistic problems beyond theoretical physics.

本文言語English
論文番号024005
ジャーナルjournal of the physical society of japan
86
2
DOI
出版ステータスPublished - 2017
外部発表はい

ASJC Scopus subject areas

  • 物理学および天文学(全般)

フィンガープリント

「Singular-value-decomposition analysis of associative memory in a neural network」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