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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Memory is a key component of biological neural systems that enables theretention of information over a huge range of temporal scales, ranging fromhundreds of milliseconds up to years. While Hebbian plasticity is believed toplay a pivotal role in biological memory, it has so far been analyzed mostly inthe context of pattern completion and unsupervised learning. Here, we proposethat Hebbian plasticity is fundamental for computations in biological neuralsystems. We introduce a novel spiking neural network architecture that isenriched by Hebbian synaptic plasticity. We show that Hebbian enrichmentrenders spiking neural networks surprisingly versatile in terms of theircomputational as well as learning capabilities. It improves their abilities forout-of-distribution generalization, one-shot learning, cross-modal generativeassociation, language processing, and reward-based learning. As spiking neuralnetworks are the basis for energy-efficient neuromorphic hardware, this alsosuggests that powerful cognitive neuromorphic systems can be build based onthis principle.

Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity