Mendoza, Hector ; Klein, Aaron ; Feurer, Matthias ; Springenberg, Jost Tobias ; Urban, Matthias ; Burkart, Michael ; Dippel, Maximilian ; Lindauer, Marius ; Hutter, Frank
Hrsg.: 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
Buchkapitel, Bibliographie
Kurzbeschreibung (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.
| Typ des Eintrags: | Buchkapitel |
|---|---|
| Erschienen: | 2019 |
| Herausgeber: | Hutter, Frank ; Kotthoff, Lars ; Vanschoren, Joaquin |
| Autor(en): | Mendoza, Hector ; Klein, Aaron ; Feurer, Matthias ; Springenberg, Jost Tobias ; Urban, Matthias ; Burkart, Michael ; Dippel, Maximilian ; Lindauer, Marius ; Hutter, Frank |
| Art des Eintrags: | Bibliographie |
| Titel: | Towards Automatically-Tuned Deep Neural Networks |
| Sprache: | Englisch |
| Publikationsjahr: | 18 Mai 2019 |
| Ort: | Berlin |
| Verlag: | Springer |
| Buchtitel: | Automated Machine Learning - Methods, Systems, Challenges |
| Reihe: | Springer Series on Challenges in Machine Learning |
| DOI: | 10.1007/978-3-030-05318-5_7 |
| URL / URN: | https://link.springer.com/chapter/10.1007/978-3-030-05318-5_... |
| Kurzbeschreibung (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. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data and AI Systems |
| Hinterlegungsdatum: | 08 Feb 2023 09:09 |
| Letzte Änderung: | 25 Mai 2023 12:17 |
| PPN: | 507990900 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum