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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Generalization to out-of-distribution (OOD) circumstances after trainingremains a challenge for artificial agents. To improve the robustness displayedby plastic Hebbian neural networks, we evolve a set of Hebbian learning rules,where multiple connections are assigned to a single rule. Inspired by thebiological phenomenon of the genomic bottleneck, we show that by allowingmultiple connections in the network to share the same local learning rule, itis possible to drastically reduce the number of trainable parameters, whileobtaining a more robust agent. During evolution, by iteratively using simpleK-Means clustering to combine rules, our Evolve and Merge approach is able toreduce the number of trainable parameters from 61,440 to 1,920, while at thesame time improving robustness, all without increasing the number ofgenerations used. While optimization of the agents is done on a standardquadruped robot morphology, we evaluate the agents' performances on slightmorphology modifications in a total of 30 unseen morphologies. Our results addto the discussion on generalization, overfitting and OOD adaptation. To createagents that can adapt to a wider array of unexpected situations, Hebbianlearning combined with a regularising "genomic bottleneck" could be a promisingresearch direction.

Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules