Research Area:  Machine Learning
In this paper, we present a lightweight CNN model named MixNet which is easily scalable to different energy requirements in embedded platforms. The MixNet model uses two extreme bit-precisions that efficiently balances the model accuracy and energy consumption. The energy consumption in processing MixNet is managed by controlling the ratio between high-precision (16bit) and low-precision (1bit) paths. Since only two bit-precisions are required in designing a hardware accelerator, the control logic becomes simpler compared to other multi-precision accelerators. In addition, a reconfigurable multiplier is proposed to enable highly parallel MixNet computations for faster prediction and/or training. Overall, the energy efficiency in terms of run-time per unit power improves by 1.75 , 1.94 over the recently proposed reduced-precision CNN model.
Keywords:  
Author(s) Name:  Sangwoo Jung; Seungsik Moon; Youngjoo Lee; Jaeha Kung
Journal name:  IEEE/ACM International Symposium on Low Power Electronics and Design
Conferrence name:  
Publisher name:  
DOI:  10.1109/ISLPED.2019.8824978
Volume Information:  
Paper Link:   https://ieeexplore.ieee.org/abstract/document/8824978