A New Type of Neurons for Machine Learning
This is an incremental improvement for machine learning practitioners, potentially enhancing neural network performance.
The paper tackled the problem of standard neurons in neural networks by replacing the inner product with a quadratic function to create second-order neurons, resulting in improved optimization and feasibility as demonstrated through numerical examples.
In machine learning, the use of an artificial neural network is the mainstream approach. Such a network consists of layers of neurons. These neurons are of the same type characterized by the two 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 1st order neuron to the 2nd 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 2nd order neurons. Finally, further topics are discussed.