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

Application of deep convolutional spiking neural networks (SNNs) toartificial intelligence (AI) tasks has recently gained a lot of interest sinceSNNs are hardware-friendly and energy-efficient. Unlike the non-spikingcounterparts, most of the existing SNN simulation frameworks are notpractically efficient enough for large-scale AI tasks. In this paper, weintroduce SpykeTorch, an open-source high-speed simulation framework based onPyTorch. This framework simulates convolutional SNNs with at most one spike perneuron and the rank-order encoding scheme. In terms of learning rules, bothspike-timing-dependent plasticity (STDP) and reward-modulated STDP (R-STDP) areimplemented, but other rules could be implemented easily. Apart from theaforementioned properties, SpykeTorch is highly generic and capable ofreproducing the results of various studies. Computations in the proposedframework are tensor-based and totally done by PyTorch functions, which in turnbrings the ability of just-in-time optimization for running on CPUs, GPUs, orMulti-GPU platforms.

SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron