Approaches to Optimization of Spiking Neural Network Hardware Implementation

The neuromorphic approach to hardware implementation of neural networks is usually considered separately from in-memory computing. In this case, we mean the hardware execution of spiking neural networks (SNN), which are the most biologically realistic compared to deep neural network algorithms. The operation principle of SNN is that the information propagates in form of spikes (voltage pulses) and the network weights (in the training mode) is updated using the time delays in the spike sequences according to the spike time-dependent plasticity rule (STDP). This results in asynchronous operation of the networks, which significantly improves their energy efficiency. In this article optimization approaches for the architecture of SNN classifiers have been proposed. The suggested optimization approaches aimed at improving the performance of neuromorphic devices based on memristive crossbars as well as minimizing the training cost. The integration of the spiking convolutional layer and implementation of dendritic computing principles in analog feedforward SNN architectures has been considered in this paper. It was shown that both approaches allow significantly facilitating the procedure of the network training. To evaluate the performance, analog circuits of the optimized SNN-architectures were modeled and designed. The functionality of one of the architectures under study is demonstrated on an experimental prototype implemented on commercial electronic components. The cost of processing a data packet by developed SNNs was estimated. The obtained results indicate that modification of SNN architectures using the principles of dendritic computing allows not only to significantly reduce the consumption of synaptic and neuronal resource in the hardware design, but also to reduce training costs. The research performed at the Saint Petersburg Electrotechnical University was funded by the grant FSEE-2020-0013 of the Ministry of Science and Higher Education of the Russian Federation.