Premium
A new type of neurons for machine learning
Author(s) -
Fan Fenglei,
Cong Wenxiang,
Wang Ge
Publication year - 2018
Publication title -
international journal for numerical methods in biomedical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.741
H-Index - 63
eISSN - 2040-7947
pISSN - 2040-7939
DOI - 10.1002/cnm.2920
Subject(s) - artificial neural network , weighting , computer science , type (biology) , function (biology) , matching (statistics) , nonlinear system , activation function , product (mathematics) , artificial intelligence , artificial neuron , mathematics , physics , ecology , statistics , geometry , quantum mechanics , evolutionary biology , acoustics , biology
In machine learning, an artificial neural network is the mainstream approach. Such a network consists of many neurons. These neurons are of the same type characterized by the 2 features: (1) an inner product of an input vector and a matching weighting vector of trainable parameters and (2) a nonlinear excitation function. Here, we investigate the possibility of replacing the inner product with a quadratic function of the input vector, thereby upgrading the first‐order neuron to the second‐order neuron, empowering individual neurons and facilitating the optimization of neural networks. Also, numerical examples are provided to illustrate the feasibility and merits of the second‐order neurons. Finally, further topics are discussed.