English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Regardless of the marked differences between biological and artificial neuralsystems, one fundamental similarity is that they are essentially dynamicalsystems that can learn to imitate other dynamical systems, without knowingtheir governing equations. The brain is able to learn the dynamic nature of thephysical world via experience; analogously, artificial neural systems can learnthe long-term behavior of complex dynamical systems from data. Yet, preciselyhow this implicit learning occurs remains unknown. Here, we draw inspirationfrom human neuroscience and from reservoir computing to propose afirst-principles framework explicating putative mechanisms of implicitlearning. Specifically, we show that an arbitrary dynamical system implicitlylearns other dynamical attractors by embedding them into its own phase spacethrough invertible generalized synchronization. By sustaining the embeddingthrough fine-tuned feedback loops, the arbitrary dynamical system can imitatethe attractor dynamics it has learned. To evaluate the mechanism's relevance,we construct several distinct neural network models that adaptively learn andimitate multiple attractors. We observe and explain the emergence of 5 distinctphenomena reminiscent of cognitive functions: (i) imitating a dynamical systempurely from learning the time series, (ii) learning multiple attractors by asingle system, (iii) switching among the imitations of multiple attractors,either spontaneously or driven by external cues, (iv) filling-in missingvariables from incomplete observations of a learned dynamical system, and (v)deciphering superimposed input from different dynamical systems. Collectively,our findings support the notion that artificial and biological neural networkscan learn the dynamic nature of their environment, and systems within theirenvironment, through the mechanism of invertible generalized synchronization.

Invertible generalized synchronization: A putative mechanism for implicit learning in biological and artificial neural systems