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

Rapidly learning from ongoing experiences and remembering past events with aflexible memory system are two core capacities of biological intelligence.While the underlying neural mechanisms are not fully understood, variousevidence supports that synaptic plasticity plays a critical role in memoryformation and fast learning. Inspired by these results, we equip RecurrentNeural Networks (RNNs) with plasticity rules to enable them to adapt theirparameters according to ongoing experiences. In addition to the traditionallocal Hebbian plasticity, we propose a global, gradient-based plasticity rule,which allows the model to evolve towards its self-determined target. Our modelsshow promising results on sequential and associative memory tasks, illustratingtheir ability to robustly form and retain memories. In the meantime, thesemodels can cope with many challenging few-shot learning problems. Comparingdifferent plasticity rules under the same framework shows that Hebbianplasticity is well-suited for several memory and associative learning tasks;however, it is outperformed by gradient-based plasticity on few-shot regressiontasks which require the model to infer the underlying mapping. Code isavailable at https://github.com/yuvenduan/PlasticRNNs.

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs