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

• Published in: Pattern recognition Vol. 94; pp. 87 - 95
• Main Authors: Mozafari, Milad, Ganjtabesh, Mohammad, Nowzari-Dalini, Abbas, Thorpe, Simon J., Masquelier, Timothée
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2019; Elsevier
• Subjects: Cognitive science; Computer science; Deep architecture; Digit recognition; Latency coding; Neuroscience; Reward-modulated STDP; Spiking neural networks; STDP; Latency coding; Digit recognition; Reward-modulated STDP; STDP; Deep architecture; Spiking neural networks; Rewardmodulated STDP
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2019.05.015

•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. 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.