Multi-Activation Hidden Units for Neural Networks with Random Weights
Neural and Evolutionary Computing
2020-09-25 v2 Machine Learning
Abstract
Single layer feedforward networks with random weights are successful in a variety of classification and regression problems. These networks are known for their non-iterative and fast training algorithms. A major drawback of these networks is that they require a large number of hidden units. In this paper, we propose the use of multi-activation hidden units. Such units increase the number of tunable parameters and enable formation of complex decision surfaces, without increasing the number of hidden units. We experimentally show that multi-activation hidden units can be used either to improve the classification accuracy, or to reduce computations.
Cite
@article{arxiv.2009.08932,
title = {Multi-Activation Hidden Units for Neural Networks with Random Weights},
author = {Ajay M. Patrikar},
journal= {arXiv preprint arXiv:2009.08932},
year = {2020}
}
Comments
4 pages, 4 figures. arXiv admin note: substantial text overlap with arXiv:2008.10425