Mendoza, Hector ; Klein, Aaron ; Feurer, Matthias ; Springenberg, Jost Tobias ; Urban, Matthias ; Burkart, Michael ; Dippel, Maximilian ; Lindauer, Marius ; Hutter, Frank
eds.: Hutter, Frank ; Kotthoff, Lars ; Vanschoren, Joaquin (2019)
Towards Automatically-Tuned Deep Neural Networks.
In: Automated Machine Learning - Methods, Systems, Challenges
doi: 10.1007/978-3-030-05318-5_7
Book Section, Bibliographie

Abstract

Recent advances in AutoML have led to automated tools that can compete with machine learning experts on supervised learning tasks. In this work, we present two versions of Auto-Net, which provide automatically-tuned deep neural networks without any human intervention. The first version, Auto-Net 1.0, builds upon ideas from the competition-winning system Auto-sklearn by using the Bayesian Optimization method SMAC and uses Lasagne as the underlying deep learning (DL) library. The more recent Auto-Net 2.0 builds upon a recent combination of Bayesian Optimization and HyperBand, called BOHB, and uses PyTorch as DL library. To the best of our knowledge, Auto-Net 1.0 was the first automatically-tuned neural network to win competition datasets against human experts (as part of the first AutoML challenge). Further empirical results show that ensembling Auto-Net 1.0 with Auto-sklearn can perform better than either approach alone, and that Auto-Net 2.0 can perform better yet.

Send an inquiry

Show editorial Details