Hardware Platform-Aware Binarized Neural Network Model Optimization

Quang Hieu Vo, Faaiz Asim, Batyrbek Alimkhanuly, Seunghyun Lee, Lokwon Kim

Research output: Contribution to journalArticlepeer-review

Abstract

Deep Neural Networks (DNNs) have shown superior accuracy at the expense of high memory and computation requirements. Optimizing DNN models regarding energy and hardware resource requirements is extremely important for applications with resource-constrained embedded environments. Although using binary neural networks (BNNs), one of the recent promising approaches, significantly reduces the design’s complexity, accuracy degradation is inevitable when reducing the precision of parameters and output activations. To balance between implementation cost and accuracy, in addition to proposing specialized hardware accelerators for corresponding specific network models, most recent software binary neural networks have been optimized based on generalized metrics, such as FLOPs or MAC operation requirements. However, with the wide range of hardware available today, independently evaluating software network structures is not good enough to determine the final network model for typical devices. In this paper, an architecture search algorithm based on estimating the hardware performance at the design time is proposed to achieve the best binary neural network models for hardware implementation on target platforms. With the XNOR-net used as a base architecture and target platforms, including Field Programmable Gate Array (FPGA), Graphic Processing Unit (GPU), and Resistive Random Access Memory (RRAM), the proposed algorithm shows its efficiency by giving more accurate estimation for the hardware performance at the design time than FLOPs or MAC operations.

Original languageEnglish
Article number1296
JournalApplied Sciences (Switzerland)
Volume12
Issue number3
DOIs
Publication statusPublished - 1 Feb 2022

Keywords

  • Binarized Neural Networks
  • FLOPs
  • Hardware cost estimation
  • MAC operations

Fingerprint

Dive into the research topics of 'Hardware Platform-Aware Binarized Neural Network Model Optimization'. Together they form a unique fingerprint.

Cite this