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

We present a new back propagation based training algorithm for discrete-timespiking neural networks (SNN). Inspired by recent deep learning algorithms onbinarized neural networks, binary activation with a straight-through gradientestimator is used to model the leaky integrate-fire spiking neuron, overcomingthe difficulty in training SNNs using back propagation. Two SNN trainingalgorithms are proposed: (1) SNN with discontinuous integration, which issuitable for rate-coded input spikes, and (2) SNN with continuous integration,which is more general and can handle input spikes with temporal information.Neuromorphic hardware designed in 40nm CMOS exploits the spike sparsity anddemonstrates high classification accuracy (>98% on MNIST) and low energy(48.4-773 nJ/image).

Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activations