Learning Task-specific Activation Functions using Genetic Programming

Mina Basirat, Peter Roth

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.

Download


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 - Volume 5: VISAPP, ISBN 978-989-758-354-4, pages 533-540. DOI: 10.5220/0007408205330540


in Bibtex Style

@conference{visapp19,
author={Mina Basirat and Peter 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 - 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 - 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