Optimization of Neuromorphic Learning Rate Using Neural Network Simulation

Neuromorphic computers optimized to utilize artificial intelligence are currently receiving much attention.In this study, neural network circuit simulations are performed by varying the nonlinearity and learning rate to understand better the characteristics of the individual and parallel-connected synaptic devices.The simulation results show that pattern recognition accuracy tends to decrease with increasing nonlinearity, while the accuracy is achieved more gradually when the learning rate is reduced.By comparing the simulation results with actual experimental results, I find an ideal learning rate and investigate how to optimize neuromorphic computers.These findings will help design new neuromorphic computers to determine the appropriate learning rate.