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

翻译：脉冲神经网络（SNN）正迅速成为资源受限边缘系统中传统人工神经网络的一种替代方案。在本研究中，我们继续推进关于递归脉冲神经网络的最新研究方向，其中轴突延迟与网络其他参数在运行时同步学习。首个提出的方法称为DelRec，展示了递归延迟学习在SNN中的优势。在此，我们通过倡导将卷积递归连接与DelRec延迟学习机制结合使用来扩展该方法。根据我们在音频分类任务上的测试，这产生了一种更精简的架构，其内存占用更小（递归参数数量节省约99%），推理速度更快（52倍），同时保持了DelRec的准确性。我们的代码可在以下网址获取：https://github.com/luciozebendo/delrec_snn/tree/conv_delays