Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
This work addresses energy efficiency and data requirements for computer vision applications, though it is incremental in combining existing bio-inspired methods.
The authors tackled the inefficiency and data-hungry nature of deep neural networks by using a deep convolutional spiking neural network with reward-modulated spike-timing-dependent plasticity, achieving 97.2% accuracy on MNIST without an external classifier.
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.