For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Neural Networks Probability-Based PWL Sigmoid Function Approximation
Vantruong NGUYEN Jueping CAI Linyu WEI Jie CHU
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2020/09/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Biocybernetics, Neurocomputing
sigmoid function, probability, neural networks, piecewise linear approximation,
Full Text: PDF>>
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.