Towards automatically-tuned deep neural networks
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
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Anmerkungen
-
Automated Machine Learning. - Cham : Hutter, Frank; Kotthoff, Lars; Vanschoren, Joaquin [Hrsg.], 2019. - 135-149, ISBN: 978-3-030-05318-5
- Ereignis
-
Veröffentlichung
- (wo)
-
Freiburg
- (wer)
-
Universität
- (wann)
-
2024
- Urheber
-
Mendoza, Hector
Klein, Aaron
Feurer, Matthias
Springenberg, Jost Tobias
Urban, Matthias
Burkart, Michael
Dippel, Maximilian
Lindauer, Marius
Hutter, Frank
- Beteiligte Personen und Organisationen
-
Maschinelles Lernen und Natürlichsprachliche Systeme, Professur Frank Hutter
- DOI
-
10.1007/978-3-030-05318-5_7
- URN
-
urn:nbn:de:bsz:25-freidok-1542403
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
25.03.2025, 13:50 MEZ
Datenpartner
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Mendoza, Hector
- Klein, Aaron
- Feurer, Matthias
- Springenberg, Jost Tobias
- Urban, Matthias
- Burkart, Michael
- Dippel, Maximilian
- Lindauer, Marius
- Hutter, Frank
- Maschinelles Lernen und Natürlichsprachliche Systeme, Professur Frank Hutter
- Universität
Entstanden
- 2024
Ähnliche Objekte (12)
Automatically estimating emotion in music with deep long-short term memory recurrent neural networks
Towards designing inherently interpretable deep neural networks for image classification
DeepBase: Deep Inspection of Neural Networks
Training deep quantum neural networks
Towards robustifying deep neural networks against adversarial, fringe and distorted examples
Deep Neural Networks motivated by PDEs
Operator compression with deep neural networks
Deep neural networks and PIDE discretizations
Optimization landscape of deep neural networks
Formal Analysis of Deep Binarized Neural Networks
Assessing the reliability of deep neural networks
Automatic drum transcription with deep neural networks
Automatically estimating emotion in music with deep long-short term memory recurrent neural networks
Towards designing inherently interpretable deep neural networks for image classification
DeepBase: Deep Inspection of Neural Networks
Training deep quantum neural networks
Towards robustifying deep neural networks against adversarial, fringe and distorted examples
Deep Neural Networks motivated by PDEs
Operator compression with deep neural networks
Deep neural networks and PIDE discretizations
Optimization landscape of deep neural networks
Formal Analysis of Deep Binarized Neural Networks
Assessing the reliability of deep neural networks
Automatic drum transcription with deep neural networks
Automatically estimating emotion in music with deep long-short term memory recurrent neural networks
Towards designing inherently interpretable deep neural networks for image classification
DeepBase: Deep Inspection of Neural Networks
Training deep quantum neural networks
Towards robustifying deep neural networks against adversarial, fringe and distorted examples
Deep Neural Networks motivated by PDEs
Operator compression with deep neural networks
Deep neural networks and PIDE discretizations
Optimization landscape of deep neural networks
Formal Analysis of Deep Binarized Neural Networks
Assessing the reliability of deep neural networks