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

This paper presents a constructive algorithm that achieves successfulone-shot learning of hidden spike-patterns in a competitive detection task. Ithas previously been shown (Masquelier et al., 2008) that spike-timing-dependentplasticity (STDP) and lateral inhibition can result in neurons competitivelytuned to repeating spike-patterns concealed in high rates of overallpresynaptic activity. One-shot construction of neurons with synapse weightscalculated as estimates of converged STDP outcomes results in immediateselective detection of hidden spike-patterns. The capability of continuallearning is demonstrated through the successful one-shot detection of new setsof spike-patterns introduced after long intervals in the simulation time.Simulation expansion (Lightheart et al., 2013) has been proposed as an approachto the development of constructive algorithms that are compatible withsimulations of biological neural networks. A simulation of a biological neuralnetwork may have orders of magnitude fewer neurons and connections than therelated biological neural systems; therefore, simulated neural networks can beassumed to be a subset of a larger neural system. The constructive algorithm isdeveloped using simulation expansion concepts to perform an operationequivalent to the exchange of neurons between the simulation and the largerhypothetical neural system. The dynamic selection of neurons to simulate withina larger neural system (hypothetical or stored in memory) may be a startingpoint for a wide range of developments and applications in machine learning andthe simulation of biology.

Continual One-Shot Learning of Hidden Spike-Patterns with Neural Network Simulation Expansion and STDP Convergence Predictions