mlsanityData to 13 Oct 2026

A Time Encoding approach to training Spiking Neural Networks

arXiv 2110.06735 ↗First posted 13 Oct 2021cs.NE cs.LG eess.SPcited by 1

Not on the map. Why?

Abstract (arXiv)

While Spiking Neural Networks (SNNs) have been gaining in popularity, it seems that the algorithms used to train them are not powerful enough to solve the same tasks as those tackled by classical Artificial Neural Networks (ANNs). In this paper, we provide an extra tool to help us understand and train SNNs by using theory from the field of time encoding. Time encoding machines (TEMs) can be used to model integrate-and-fire neurons and have well-understood reconstruction properties. We will see how one can take inspiration from the field of TEMs to interpret the spike times of SNNs as constraints on the SNNs' weight matrices. More specifically, we study how to train one-layer SNNs by solving a set of linear constraints, and how to train two-layer SNNs by leveraging the all-or-none and asynchronous properties of the spikes emitted by SNNs. These properties of spikes result in an alternative to backpropagation which is not possible in the case of simultaneous and graded activations as in classical ANNs.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 10 of its 27 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

10 of 27 references.

References · 10

  1. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 617
  2. 2020Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networkscited by 59
  3. 2019Temporal Coding in Spiking Neural Networks with Alpha Synaptic Function: Learning with Backpropagationcited by 45
  4. 2021Learning from Event Cameras with Sparse Spiking Convolutional Neural Networkscited by 25
  5. 2019Reconstructing Classes of Non-bandlimited Signals from Time Encoded Informationcited by 4
  6. 2019Sampling and Reconstruction of Bandlimited Signals with Multi-Channel Time Encodingcited by 4
  7. 2021Asynchrony Increases Efficiency: Time Encoding of Videos and Low-Rank Signalscited by 4
  8. 2019Encoding and Decoding Mixed Bandlimited Signals using Spiking Integrate-and-Fire Neuronscited by 2
  9. 2020Matrix recovery from bilinear and quadratic measurementscited by 2
  10. 2021Time Encoding of Finite-Rate-of-Innovation Signalscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022How Asynchronous Events Encode Videocited by 0