Learning Task-specific Activation Functions using Genetic Programming

Mina Basirat, Peter M. Roth

2019

Abstract

Deep Neural Networks have been shown to be beneficial for a variety of tasks, in particular allowing for end-to-end learning and reducing the requirement for manual design decisions. However, still many parameters have to be chosen manually in advance, also raising the need to optimize them. One important, but often ignored parameter is the selection of a proper activation function. In this paper, we tackle this problem by learning task-specific activation functions by using ideas from genetic programming. We propose to construct piece-wise activation functions (for the negative and the positive part) and introduce new genetic operators to combine functions in a more efficient way. The experimental results for multi-class classification demonstrate that for different tasks specific activation functions are learned, also outperforming widely used generic baselines.

Paper Citation

in Harvard Style

Basirat M. and Roth P. (2019). Learning Task-specific Activation Functions using Genetic Programming. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 533-540. DOI: 10.5220/0007408205330540

in Bibtex Style

@conference{visapp19,
author={Mina Basirat and Peter M. Roth},
title={Learning Task-specific Activation Functions using Genetic Programming},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={533-540},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007408205330540},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Learning Task-specific Activation Functions using Genetic Programming
SN - 978-989-758-354-4
AU - Basirat M.
AU - Roth P.
PY - 2019
SP - 533
EP - 540
DO - 10.5220/0007408205330540
PB - SciTePress