Towards Automatically-Tuned Neural Networks
Abstract
Recent advances in AutoML have led to automated tools that can compete with machine learning experts on supervised learning tasks. However, current AutoML tools do not yet support modern neural networks effectively. In this work, we present a first version of Auto-Net, which provides automatically-tuned feed-forward neural networks without any human intervention. We report results on datasets from the recent AutoML challenge showing that ensembling Auto-Net with Auto-sklearn often performs better than either alone, and report the first results on winning a competition dataset against human experts with automatically-tuned neural networks.
Cite
Text
Mendoza et al. "Towards Automatically-Tuned Neural Networks." Proceedings of the Workshop on Automatic Machine Learning, 2016.Markdown
[Mendoza et al. "Towards Automatically-Tuned Neural Networks." Proceedings of the Workshop on Automatic Machine Learning, 2016.](https://mlanthology.org/automl/2016/mendoza2016automl-automaticallytuned/)BibTeX
@inproceedings{mendoza2016automl-automaticallytuned,
title = {{Towards Automatically-Tuned Neural Networks}},
author = {Mendoza, Hector and Klein, Aaron and Feurer, Matthias and Springenberg, Jost Tobias and Hutter, Frank},
booktitle = {Proceedings of the Workshop on Automatic Machine Learning},
year = {2016},
pages = {58-65},
volume = {64},
url = {https://mlanthology.org/automl/2016/mendoza2016automl-automaticallytuned/}
}