Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Combining Convolution and Delay Learning in Recurrent Spiking Neural Networks

About

Spiking neural networks (SNNs) are rapidly gaining momentum as an alternative to conventional artificial neural networks in resource constrained edge systems. In this work, we continue a recent research line on recurrent SNNs where axonal delays are learned at runtime along with the other network parameters. The first proposed approach, dubbed DelRec, demonstrated the benefit of recurrent delay learning in SNNs. Here, we extend it by advocating the use of convolutional recurrent connections in conjunction with the DelRec delay learning mechanism. According to our tests on an audio classification task, this leads to a streamlined architecture with smaller memory footprint (around 99% savings in terms of number of recurrent parameters) and a much faster (52x) inference time, while retaining DelRec's accuracy. Our code is available at: https://github.com/luciozebendo/delrec_snn/tree/conv_delays

L\'ucio Folly Sanches Zebendo, Eleonora Cicciarella, Michele Rossi• 2026

Related benchmarks

TaskDatasetResultRank
Audio ClassificationSHD (test)
Accuracy91.51
41
Sound RecognitionSSC (test)
Accuracy78.59
6
Showing 2 of 2 rows

Other info

Follow for update