A Novel Weight Dropout Approach to Accelerate the Neural Network Controller Embedded Implementation on FPGA for a Solar Inverter

This paper introduces a novel weight-dropout approach to train a neural network controller in real-time closed-loop control and to accelerate the embedded implementation for a solar inverter. The essence of the approach is to drop small-magnitude weights of neural network controllers during training with the goal of minimizing the required numbers of connections and guaranteeing the convergence of the neural network controllers. In order not to affect the convergence of neural network controllers, only non-diagonal elements of the neural network weight matrices were dropped. The dropout approach was incorporated into Levenberg-Marquardt and Forward Accumulation Through Time algorithms to train the neural network controller for trajectory tracking more efficiently. The Field Programmable Gate Array (FPGA) implementation on the Intel Cyclone V board shows significant improvement in terms of computation and resource requirements using the sparse weight matrices after dropout, which makes the neural network controller more suitable in an embedded environment.