Towards a mathematical framework to inform neural network modelling via polynomial regression

P Morala, JA Cifuentes, RE Lillo, I Ucar - Neural Networks, 2021 - Elsevier
Even when neural networks are widely used in a large number of applications, they are still
considered as black boxes and present some difficulties for dimensioning or evaluating their …

Deep Learning-Enhanced ICA Algorithm for Sub-Gaussian Blind Source Separation

Z Xie, Z Sun, G Yue, J Fan - … Conference on Artificial Intelligence in China, 2022 - Springer
In the conventional iterative blind source separation procedure, the nonlinear function is
selected as a fixed mathematical expression that cannot change with different signals. In this …