Spiking recurrent neural networks for neuromorphic computing in nonlinear structural mechanics

Abstract

The present study aims to introduce an AI algorithm suitable for neuromorphic computing to solve Boundary Value Problems in Engineering Mechanics. Following the trend of sustainable Artificial Intelligence (AI), Spiking Neural Networks (SNNs), known as the third generation of neural networks, are proposed for developing surrogate models for mechanical tasks. SNNs are inherently recurrent and communicate through sparse signals consuming only a fraction of the energy needed by artificial neural networks (ANNs) of the second generation such as current deep learning methods. To take advantage of the energy-efficient spike models, an autoencoding strategy is proposed to convert the real-valued data at a certain time step to its binary spike representation which allows the model to be used for regression tasks. Further, we propose a hybrid model consisting of the spiking variant of the Legendre Memory Unit (LMU), spiking recurrent cells, and classical dense transformations to compute the nonlinear (physically and geometrically) response of shock wave-loaded plate elements. The inclusion of spikes enables the proposed model to be deployed on neuromorphic hardware, such as the Loihi chip. Thus, for a series of both training and validation experiments, a detailed comparison of the proposed hybrid model and its second-generation counterpart in terms of energy consumption and accuracy is presented.