Reservoir-computing based associative memory and itinerancy for complex dynamical attractors

Traditional neural network models of associative memories were used to store and retrieve static patterns. We develop reservoir-computing based memories for complex dynamical attractors, under two common recalling scenarios in neuropsychology: location-addressable with an index channel and content-a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nature communications Jg. 15; H. 1; S. 4840 - 14
Hauptverfasser: Kong, Ling-Wei, Brewer, Gene A., Lai, Ying-Cheng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 06.06.2024
Nature Publishing Group
Nature Portfolio
Schlagworte:
639/705/1042
639/705/117
Associative memory
Attractors (mathematics)
Complex systems
Computation
Dynamical systems
Humanities and Social Sciences
multidisciplinary
Neural networks
Retrieval
Science
Science (multidisciplinary)
Switching
ISSN:2041-1723, 2041-1723
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Traditional neural network models of associative memories were used to store and retrieve static patterns. We develop reservoir-computing based memories for complex dynamical attractors, under two common recalling scenarios in neuropsychology: location-addressable with an index channel and content-addressable without such a channel. We demonstrate that, for location-addressable retrieval, a single reservoir computing machine can memorize a large number of periodic and chaotic attractors, each retrievable with a specific index value. We articulate control strategies to achieve successful switching among the attractors, unveil the mechanism behind failed switching, and uncover various scaling behaviors between the number of stored attractors and the reservoir network size. For content-addressable retrieval, we exploit multistability with cue signals, where the stored attractors coexist in the high-dimensional phase space of the reservoir network. As the length of the cue signal increases through a critical value, a high success rate can be achieved. The work provides foundational insights into developing long-term memories and itinerancy for complex dynamical patterns. Artificial associative memories in neural network models have shown ability to store and retrieve static patterns of complex systems, however analysis of dynamic patterns remains challenging. The authors develop a reservoir computing based memory approach for complex multistable dynamical systems.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-024-49190-4