Development of Parameter Bit Operation Framework for Deep Neural Networks

Dong In Lee, Jung-Heon Kim, Seung-Ho Lim

Abstract: Recently, research on lightweighting of Deep Neural Network(DNN) models suitable for embedded IoT devices and edge computing is rapidly increasing. One of the important points of lightweighting DNN is model parameter optimization. Parameter precision increases model accuracy, but also increases memory and processing overhead. In this paper, we developed a parameter bitwise adjustment framework of DNN models to analyze the correlation between model’s parameter precision and performance. The framework can set each bit of parameter value to 0, 1, or random in a specific range for DNN models. With the framework we measured the accuracy of the model while modifying the parameter values to 0 by step by step from LSB, for three representative CNN models. As a result, it was identified that the accuracy robustness for the range of valid parameters is different each other depending on the model.