Brain-inspired reservoir computing framework for complex time-series prediction

Abstract

Summary Time-series prediction based on historical data is essential in numerous scientific fields, such as weather prediction and financial markets analysis. However, obtaining strong predictive accuracy together with high computational efficiency remains challenging. To address this challenge, we propose a brain-inspired neural network-based echo state network (BINN-ESN). It uses a modified continuous coupled neural network (MCCNN) as the neural model, which is inspired by the mammalian visual cortex. Our results indicate a system-dependent trade-off: While deep learning baselines generally achieve stronger single-step accuracy, BINN-ESN shows stronger long-term predictive stability on most evaluated systems and requires substantially less total computation than the GPU-accelerated long short-term memory (LSTM) baseline in long-term experiments. Our code is available at https://github.com/Jizhao-Liu/code-for-BINN-ESN.