Deep Unsupervised Learning Using Spike-Timing-Dependent Plasticity
This work addresses a bottleneck in neuromorphic hardware by enabling deeper unsupervised learning with STDP, though it appears incremental as it builds on existing STDP methods.
The paper tackles the challenge of scaling Spike-Timing-Dependent Plasticity (STDP) for deep Spiking Neural Networks by introducing a Deep-STDP framework that combines rate-based convolutional networks with pseudo-labels from STDP clustering, achieving 24.56% higher accuracy and 3.5x faster convergence on a Tiny ImageNet subset compared to k-means.
Spike-Timing-Dependent Plasticity (STDP) is an unsupervised learning mechanism for Spiking Neural Networks (SNNs) that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve $24.56\%$ higher accuracy and $3.5\times$ faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a $k$-means clustering approach.