Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks. (October 2019)

• Record Type: Journal Article
• Authors: Mozafari, Milad; Ganjtabesh, Mohammad; Nowzari-Dalini, Abbas; Thorpe, Simon J.; Masquelier, Timothée
• Is Part Of: Pattern recognition. Volume 94(2019:Oct.)
• Page Start: 87
• Page End: 95
• Publication Date: 2019-10
• Subjects: Spiking neural networks -- Deep architecture -- Digit recognition -- STDP -- Reward-modulated STDP -- Latency coding; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.05.015
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We used a bio-inspired deep convolutional spiking neural network with latency-coding. We trained the low (resp. top) layers with STDP (resp. reward-modulated STDP). Accuracy was 97.2% on MNIST, without requiring an external classifier. Reward-modulated STDP favors diagnostic features, while STDP favors frequent ones. The proposed neuron-based decision-making layer is suitable for energy-efficient hardware implementation. 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.