Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks

TL;DR

This paper presents a biologically inspired deep spiking neural network trained with reward-modulated STDP, achieving high accuracy on MNIST while being energy-efficient and hardware-friendly.

Contribution

It introduces a novel training scheme combining STDP and R-STDP in deep convolutional spiking networks for digit recognition.

Findings

Achieved 97.2% accuracy on MNIST without external classifiers.

R-STDP extracts task-relevant features, discarding irrelevant ones.

The approach is biologically plausible and energy-efficient.

Abstract

The primate visual system has inspired the development of deep artificial neural networks, which have revolutionized the computer vision domain. Yet these networks are much less energy-efficient than their biological counterparts, and they are typically trained with backpropagation, which is extremely data-hungry. To address these limitations, we used a deep convolutional spiking neural network (DCSNN) and a latency-coding scheme. We trained it using a combination of spike-timing-dependent plasticity (STDP) for the lower layers and reward-modulated STDP (R-STDP) for the higher ones. In short, with R-STDP a correct (resp. incorrect) decision leads to STDP (resp. anti-STDP). This approach led to an accuracy of $97.2\%$ on MNIST, without requiring an external classifier. In addition, we demonstrated that R-STDP extracts features that are diagnostic for the task at hand, and discards the other ones, whereas STDP extracts any feature that repeats. Finally, our approach is biologically plausible, hardware friendly, and energy-efficient.