The search functionality is under construction.
The search functionality is under construction.

Neural Networks Probability-Based PWL Sigmoid Function Approximation

Vantruong NGUYEN, Jueping CAI, Linyu WEI, Jie CHU

  • Full Text Views

    0

  • Cite this

Summary :

In this letter, a piecewise linear (PWL) sigmoid function approximation based on the statistical distribution probability of the neurons' values in each layer is proposed to improve the network recognition accuracy with only addition circuit. The sigmoid function is first divided into three fixed regions, and then according to the neurons' values distribution probability, the curve in each region is segmented into sub-regions to reduce the approximation error and improve the recognition accuracy. Experiments performed on Xilinx's FPGA-XC7A200T for MNIST and CIFAR-10 datasets show that the proposed method achieves 97.45% recognition accuracy in DNN, 98.42% in CNN on MNIST and 72.22% on CIFAR-10, up to 0.84%, 0.57% and 2.01% higher than other approximation methods with only addition circuit.

Publication
IEICE TRANSACTIONS on Information Vol.E103-D No.9 pp.2023-2026
Publication Date
2020/09/01
Publicized
2020/06/11
Online ISSN
1745-1361
DOI
10.1587/transinf.2020EDL8007
Type of Manuscript
LETTER
Category
Biocybernetics, Neurocomputing

Authors

Vantruong NGUYEN
  Xidian University
Jueping CAI
  Xidian University
Linyu WEI
  Xidian University
Jie CHU
  Xidian University

Keyword