Vector Field Based Neural Networks
Abstract
A novel Neural Network architecture is proposed using the mathematically and physically rich idea of vector fields as hidden layers to perform nonlinear transformations in the data. The data points are interpreted as particles moving along a flow defined by the vector field which intuitively represents the desired movement to enable classification. The architecture moves the data points from their original configuration to anew one following the streamlines of the vector field with the objective of achieving a final configuration where classes are separable. An optimization problem is solved through gradient descent to learn this vector field.
Cite
@article{arxiv.1802.08235,
title = {Vector Field Based Neural Networks},
author = {Daniel Vieira and Fabio Rangel and Fabricio Firmino and Joao Paixao},
journal= {arXiv preprint arXiv:1802.08235},
year = {2018}
}
Comments
6 pages, 5 figures. To appear in the Proceedings of the 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning