Performance Improvement of Memristor-Based Echo State Networks by Optimized Programming Scheme
Jie Yu, Wenxuan Sun, Jinru Lai, Xu Zheng, Danian Dong, Qing Luo, Hangbing Lv, Xiaoxin Xu
Abstract
The Echo State Networks (ESNs) is a class of recurrent neural network (RNN), which can significantly reduce the training complexity since the input layer and middle layer (reservoir) are random fixed networks. In this letter, we propose a hardware-software co-design platform to implement memristor crossbar arrays for ESN model. We propose the programming with delayed pulse (PDP) scheme to improve the network performance by suppressing the degradation of the memristor. We optimized the spectral radius (SR) of the ESNs model. In addition, the programming scheme can also effectively improve the timing prediction capability of the memristor-based ESN network. When the prediction length is set to 1000, the Normalized Root Mean Square Error (NRMSE) of the ESN can be optimized by 56 times.