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

Spiking neural networks (SNNs) have attracted much attention due to theirability to process temporal information, low power consumption, and higherbiological plausibility. However, it is still challenging to develop efficientand high-performing learning algorithms for SNNs. Methods like artificialneural network (ANN)-to-SNN conversion can transform ANNs to SNNs with slightperformance loss, but it needs a long simulation to approximate the ratecoding. Directly training SNN by spike-based backpropagation (BP) such assurrogate gradient approximation is more flexible. Yet now, the performance ofSNNs is not competitive compared with ANNs. In this paper, we propose a novelk-based leaky Integrate-and-Fire (KLIF) neuron model to improve the learningability of SNNs. Compared with the popular leaky integrate-and-fire (LIF)model, KLIF adds a learnable scaling factor to dynamically update the slope andwidth of the surrogate gradient curve during training and incorporates a ReLUactivation function that selectively delivers membrane potential to spikefiring and resetting. The proposed spiking unit is evaluated on both staticMNIST, Fashion-MNIST, CIFAR-10 datasets, as well as neuromorphic N-MNIST,CIFAR10-DVS, and DVS128-Gesture datasets. Experiments indicate that KLIFperforms much better than LIF without introducing additional computational costand achieves state-of-the-art performance on these datasets with few timesteps. Also, KLIF is believed to be more biological plausible than LIF. Thegood performance of KLIF can make it completely replace the role of LIF in SNNfor various tasks.

KLIF: An optimized spiking neuron unit for tuning surrogate gradient slope and membrane potential