Plug and Play Deep Convolutional Neural Networks

Patrick Neary, Vicki Allan

2019

Abstract

Major gains have been made in recent years in object recognition due to advances in deep convolutional neural networks. One struggle with deep learning is identifying an optimal network architecture for a given problem. Often different configurations are tried until one is identified that gives acceptable results. This paper proposes an asynchronous learning algorithm that finds an optimal network configuration by automatically adjusting network hyperparameters.

Paper Citation

in Harvard Style

Neary P. and Allan V. (2019). Plug and Play Deep Convolutional Neural Networks.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 388-395. DOI: 10.5220/0007255103880395

in Bibtex Style

@conference{icaart19,
author={Patrick Neary and Vicki Allan},
title={Plug and Play Deep Convolutional Neural Networks},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={388-395},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007255103880395},
isbn={978-989-758-350-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Plug and Play Deep Convolutional Neural Networks
SN - 978-989-758-350-6
AU - Neary P.
AU - Allan V.
PY - 2019
SP - 388
EP - 395
DO - 10.5220/0007255103880395