SemiMul: Floating-Point Free Implementations for Efficient and Accurate Neural Network Training

Ali Nezhadi, Shaahin Angizi, Arman Roohi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Multiply-accumulate operation (MAC) is a fundamental component of machine learning tasks, where multiplication (either integer or float multiplication) compared to addition is costly in terms of hardware implementation or power consumption. In this paper, we approximate floating-point multiplication by converting it to integer addition while preserving the test accuracy of shallow and deep neural networks. We mathematically show and prove that our proposed method can be utilized with any floating-point format (e.g., FP8, FP16, FP32, etc.). It is also highly compatible with conventional hardware architectures and can be employed in CPU, GPU, or ASIC accelerators for neural network tasks with minimum hardware cost. Moreover, the proposed method can be utilized in embedded processors without a floating-point unit to perform neural network tasks. We evaluated our method on various datasets such as MNIST, FashionMNIST, SVHN, Cifar-10, and Cifar-100, with both FP16 and FP32 arithmetics. The proposed method preserves the test accuracy and, in some cases, overcomes the overfitting problem and improves the test accuracy.

Original languageEnglish (US)
Title of host publicationProceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022
EditorsM. Arif Wani, Mehmed Kantardzic, Vasile Palade, Daniel Neagu, Longzhi Yang, Kit-Yan Chan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages837-842
Number of pages6
ISBN (Electronic)9781665462839
DOIs
StatePublished - 2022
Event21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022 - Nassau, Bahamas
Duration: Dec 12 2022Dec 14 2022

Publication series

NameProceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022

Conference

Conference21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022
Country/TerritoryBahamas
CityNassau
Period12/12/2212/14/22

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Artificial Intelligence
  • Hardware and Architecture

Keywords

  • Approximate Computing
  • Machine Learning
  • Neural Networks

Fingerprint

Dive into the research topics of 'SemiMul: Floating-Point Free Implementations for Efficient and Accurate Neural Network Training'. Together they form a unique fingerprint.

Cite this