Superiority of quadratic over conventional neural networks for classification of gaussian mixture data

Superiority of quadratic over conventional neural networks for classification of gaussian mixture data

Abstract To enrich the diversity of artificial neurons, a type of quadratic neurons was proposed previously, where the inner product of inputs and weights is replaced by a quadratic operation. In this paper, we demonstrate the superiority of such quadratic neurons over conventional counterparts. For...

Full description

Bibliographic Details
Main Authors: Tianrui Qi, Ge Wang
Format: Article
Language:English
Published: SpringerOpen 2022-09-01
Series:Visual Computing for Industry, Biomedicine, and Art
Subjects:
Artificial neural networks
Quadratic neurons
Quadratic neural networks
Backpropagation
Classification
Gaussian mixture models
Online Access:https://doi.org/10.1186/s42492-022-00118-z

Internet

https://doi.org/10.1186/s42492-022-00118-z

Similar Items