Unsupervised visual feature learning with spike-timing-dependent plasticity: How far are we from traditional feature learning approaches?

作者：

Highlights：

• We compare the performance of spiking neural networks (SNNs) with auto-encoders for visual feature learning.

• Results show that current SNNs are not competitive with autoencoders.

• From the analysis of the results, we identify some bottlenecks that should be addressed to make SNNs competitive with state-of-the-art systems.

摘要

•We compare the performance of spiking neural networks (SNNs) with auto-encoders for visual feature learning.•Results show that current SNNs are not competitive with autoencoders.•From the analysis of the results, we identify some bottlenecks that should be addressed to make SNNs competitive with state-of-the-art systems.

论文关键词：Feature learning,Unsupervised learning,Spiking neural networks,Spike-timing dependent plasticity,Auto-encoders,Image recognition

论文评审过程：Received 30 June 2018, Revised 30 March 2019, Accepted 16 April 2019, Available online 17 April 2019, Version of Record 9 May 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.016