A New Look at Spike-Timing-Dependent Plasticity Networks for Spatio-Temporal Feature Learning
This work addresses the need for efficient and biologically-plausible learning in neuromorphic edge devices, offering incremental advances in theoretical optimization for event-based vision.
The paper tackles the problem of unsupervised spatio-temporal feature learning in spiking neural networks by providing new theoretical foundations for Spike-Timing-Dependent Plasticity parameter tuning, resulting in significant accuracy improvements such as +8.2% on CIFAR10-DVS and +9.3% on N-MNIST compared to state-of-the-art methods.
We present new theoretical foundations for unsupervised Spike-Timing-Dependent Plasticity (STDP) learning in spiking neural networks (SNNs). In contrast to empirical parameter search used in most previous works, we provide novel theoretical grounds for SNN and STDP parameter tuning which considerably reduces design time. Using our generic framework, we propose a class of global, action-based and convolutional SNN-STDP architectures for learning spatio-temporal features from event-based cameras. We assess our methods on the N-MNIST, the CIFAR10-DVS and the IBM DVS128 Gesture datasets, all acquired with a real-world event camera. Using our framework, we report significant improvements in classification accuracy compared to both conventional state-of-the-art event-based feature descriptors (+8.2% on CIFAR10-DVS), and compared to state-of-the-art STDP-based systems (+9.3% on N-MNIST, +7.74% on IBM DVS128 Gesture). Our work contributes to both ultra-low-power learning in neuromorphic edge devices, and towards a biologically-plausible, optimization-based theory of cortical vision.