TY - JOUR
T1 - On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights
AU - Yu , Dansheng
AU - Qian , Yunyou
AU - Li , Fengjun
JO - Analysis in Theory and Applications
VL - 1
SP - 93
EP - 104
PY - 2023
DA - 2023/03
SN - 39
DO - http://doi.org/10.4208/ata.OA-2021-0006
UR - https://global-sci.org/intro/article_detail/ata/21464.html
KW - Approximation rate, modulus of continuity, modulus of smoothness, neural network operators.
AB - <p style="text-align: justify;">Recently, Li [16] introduced three kinds of single-hidden layer feed-forward
neural networks with optimized piecewise linear activation functions and fixed
weights, and obtained the upper and lower bound estimations on the approximation
accuracy of the FNNs, for continuous function defined on bounded intervals. In the
present paper, we point out that there are some errors both in the definitions of the
FNNs and in the proof of the upper estimations in [16]. By using new methods, we
also give right approximation rate estimations of the approximation by Li’s neural
networks.</p>