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

One of the key challenges in training Spiking Neural Networks (SNNs) is thattarget outputs typically come in the form of natural signals, such as labelsfor classification or images for generative models, and need to be encoded intospikes. This is done by handcrafting target spiking signals, which in turnimplicitly fixes the mechanisms used to decode spikes into natural signals,e.g., rate decoding. The arbitrary choice of target signals and decoding rulegenerally impairs the capacity of the SNN to encode and process information inthe timing of spikes. To address this problem, this work introduces a hybridvariational autoencoder architecture, consisting of an encoding SNN and adecoding Artificial Neural Network (ANN). The role of the decoding ANN is tolearn how to best convert the spiking signals output by the SNN into the targetnatural signal. A novel end-to-end learning rule is introduced that optimizes adirected information bottleneck training criterion via surrogate gradients. Wedemonstrate the applicability of the technique in an experimental settings onvarious tasks, including real-life datasets.

Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck