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

In this article, we propose a novel Winner-Take-All (WTA) architectureemploying neurons with nonlinear dendrites and an online unsupervisedstructural plasticity rule for training it. Further, to aid hardwareimplementations, our network employs only binary synapses. The proposedlearning rule is inspired by spike time dependent plasticity (STDP) but differsfor each dendrite based on its activation level. It trains the WTA networkthrough formation and elimination of connections between inputs and synapses.To demonstrate the performance of the proposed network and learning rule, weemploy it to solve two, four and six class classification of random Poissonspike time inputs. The results indicate that by proper tuning of the inhibitorytime constant of the WTA, a trade-off between specificity and sensitivity ofthe network can be achieved. We use the inhibitory time constant to set thenumber of subpatterns per pattern we want to detect. We show that while thepercentage of successful trials are 92%, 88% and 82% for two, four and sixclass classification when no pattern subdivisions are made, it increases to100% when each pattern is subdivided into 5 or 10 subpatterns. However, theformer scenario of no pattern subdivision is more jitter resilient than thelater ones.

An Online Unsupervised Structural Plasticity Algorithm for Spiking Neural Networks