Activation Functions: Do They Represent A Trade-Off Between Modular Nature of Neural Networks And Task Performance
Machine Learning
2020-09-17 v1 Machine Learning
Abstract
Current research suggests that the key factors in designing neural network architectures involve choosing number of filters for every convolution layer, number of hidden neurons for every fully connected layer, dropout and pruning. The default activation function in most cases is the ReLU, as it has empirically shown faster training convergence. We explore whether ReLU is the best choice if one is aiming to desire better modularity structure within a neural network.
Cite
@article{arxiv.2009.07793,
title = {Activation Functions: Do They Represent A Trade-Off Between Modular Nature of Neural Networks And Task Performance},
author = {Himanshu Pradeep Aswani and Amit Sethi},
journal= {arXiv preprint arXiv:2009.07793},
year = {2020}
}
Comments
5 pages, 1 figure, 2 tables, pre-print