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

Neural population activity relating to behaviour is assumed to be inherentlylow-dimensional despite the observed high dimensionality of data recorded usingmulti-electrode arrays. Therefore, predicting behaviour from neural populationrecordings has been shown to be most effective when using latent variablemodels. Over time however, the activity of single neurons can drift, anddifferent neurons will be recorded due to movement of implanted neural probes.This means that a decoder trained to predict behaviour on one day performsworse when tested on a different day. On the other hand, evidence suggests thatthe latent dynamics underlying behaviour may be stable even over months andyears. Based on this idea, we introduce a model capable of inferringbehaviourally relevant latent dynamics from previously unseen data recordedfrom the same animal, without any need for decoder recalibration. We show thatunsupervised domain adaptation combined with a sequential variationalautoencoder, trained on several sessions, can achieve good generalisation tounseen data and correctly predict behaviour where conventional methods fail.Our results further support the hypothesis that behaviour-related neuraldynamics are low-dimensional and stable over time, and will enable moreeffective and flexible use of brain computer interface technologies.

Robust alignment of cross-session recordings of neural population activity by behaviour via unsupervised domain adaptation