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

Learning based on networks of real neurons, and by extension biologicallyinspired models of neural networks, has yet to find general learning rulesleading to widespread applications. In this paper, we argue for the existenceof a principle allowing to steer the dynamics of a biologically inspired neuralnetwork. Using carefully timed external stimulation, the network can be driventowards a desired dynamical state. We term this principle "Learning byStimulation Avoidance" (LSA). We demonstrate through simulation that theminimal sufficient conditions leading to LSA in artificial networks are alsosufficient to reproduce learning results similar to those obtained inbiological neurons by Shahaf and Marom [1]. We examine the mechanism's basicdynamics in a reduced network, and demonstrate how it scales up to a network of100 neurons. We show that LSA has a higher explanatory power than existinghypotheses about the response of biological neural networks to externalsimulation, and can be used as a learning rule for an embodied application:learning of wall avoidance by a simulated robot. The surge in popularity ofartificial neural networks is mostly directed to disembodied models of neuronswith biologically irrelevant dynamics: to the authors' knowledge, this is thefirst work demonstrating sensory-motor learning with random spiking networksthrough pure Hebbian learning.

Learning by Stimulation Avoidance: A Principle to Control Spiking Neural Networks Dynamics