Abstract
Resonance, as a ubiquitous feature across many wave systems, is a natural candidate for analog computing in temporal signals. We demonstrate that resonance can be used to construct stable and scalable recurrent neural networks. By including resonators with different lifetimes, the computing system develops both short-term and long-term memories simultaneously.
© 2023 The Author(s)
PDF ArticleMore Like This
Minhua Liang
WR.2 OSA Annual Meeting (FIO) 1993
Lauri Salmela, Coraline Lapre, John M. Dudley, and Goery Genty
STu4H.6 CLEO: Science and Innovations (CLEO:S&I) 2020
Guangwei Cong, Noritsugu Yamamoto, Rai Kou, Yuriko Maegami, Morifumi Ohno, and Koji Yamada
W3G.2 Optical Fiber Communication Conference (OFC) 2023