Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?
This work addresses the problem of evaluating SNNs for image recognition on modern datasets, but it is incremental as it identifies issues without solving them.
The paper tackled the performance gap between spiking neural networks (SNNs) using spike-timing-dependent plasticity and traditional auto-encoders for unsupervised visual feature learning, finding that SNNs face bottlenecks like on-center/off-center coding limits and ineffective inhibition mechanisms, especially on color images.
Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features without supervision and can be implemented by ultra-low power hardware architectures. However, their performance in image classification has never been evaluated on recent image datasets. In this paper, we compare SNNs to auto-encoders on three visual recognition datasets, and extend the use of SNNs to color images. The analysis of the results helps us identify some bottlenecks of SNNs: the limits of on-center/off-center coding, especially for color images, and the ineffectiveness of current inhibition mechanisms. These issues should be addressed to build effective SNNs for image recognition.