Open AccessAn adaptive RBF hidden layer generation algorithm
Author(s) -
Haibo Chen,
Chenyu Zhang,
Gao Hu
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/7/072097
Subject(s) - computer science , algorithm , layer (electronics) , artificial neural network , sample (material) , sensitivity (control systems) , artificial intelligence , pattern recognition (psychology) , engineering , chemistry , organic chemistry , chromatography , electronic engineering
We presents an adaptive learning algorithm of RBF neural network. This algorithm uses an adaptive splitting operation based on network sensitivity and sample density to dynamically change the number of nodes in the hidden layer of RBF network. At the same time, a refactoring operation based on energy consumption is proposed, and the connection weights of the hidden layer and the output layer are obtained by using the least square method. In the experiment of iris sample classification, the recognition rate of the model is 95%.