English

Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing

Neural and Evolutionary Computing 2018-05-14 v1 Emerging Technologies

Abstract

Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications. Nevertheless, the deep structure has brought significant increases in computation complexity. Largescale deep learning systems mainly operate in high-performance server clusters, thus restricting the application extensions to personal or mobile devices. Previous works on GPU and/or FPGA acceleration for DCNNs show increasing speedup, but ignore other constraints, such as area, power, and energy. Stochastic Computing (SC), as a unique data representation and processing technique, has the potential to enable the design of fully parallel and scalable hardware implementations of large-scale deep learning systems. This paper proposed an automatic design allocation algorithm driven by budget requirement considering overall accuracy performance. This systematic method enables the automatic design of a DCNN where all design parameters are jointly optimized. Experimental results demonstrate that proposed algorithm can achieve a joint optimization of all design parameters given the comprehensive budget of a DCNN.

Keywords

Cite

@article{arxiv.1805.04142,
  title  = {Towards Budget-Driven Hardware Optimization for Deep Convolutional Neural Networks using Stochastic Computing},
  author = {Zhe Li and Ji Li and Ao Ren and Caiwen Ding and Jeffrey Draper and Qinru Qiu and Bo Yuan and Yanzhi Wang},
  journal= {arXiv preprint arXiv:1805.04142},
  year   = {2018}
}

Comments

Accepted by IEEE Computer Society Annual Symposium on VLSI 2018

R2 v1 2026-06-23T01:51:26.055Z