Analog learning neural circuit with switched capacitor and the design of deep learning model

Abstract

In the neural network field, many applicationmodels have been proposed. Previous analog neural network models were composed of the operational amplifier and fixed resistance. It is difficult to change the connecting weight of network. In this study, we used analog electronic multiple and switched capacitor circuits. The connecting weights describe the input voltage. It is easy to change the connection coefficient. This model works only on analog electronic circuits. It can finish the learning process in a very short time and this model will enablemore flexible learning. However, the structure of this model is only one input and one output network. We improved the number of unit and network layers. Moreover, we suggest the possibility of the realization of the hardware implementation of the deep learning model.