Status: Bibliographieeintrag
Standort: ---
Exemplare:
---
| Online-Ressource |
Verfasst von: | Haußmann, Manuel [VerfasserIn]  |
| Hamprecht, Fred [VerfasserIn]  |
| Kandemir, Melih [VerfasserIn]  |
Titel: | Deep active learning with adaptive acquisition |
Verf.angabe: | Manuel Haußmann, Fred Hamprecht and Melih Kandemir |
E-Jahr: | 2019 |
Jahr: | 27 Jun 2019 |
Umfang: | 7 S. |
Fussnoten: | Gesehen am 13.07.2022 |
Titel Quelle: | Enthalten in: De.arxiv.org |
Ort Quelle: | [S.l.] : Arxiv.org, 1991 |
Jahr Quelle: | 2019 |
Band/Heft Quelle: | (2019), Artikel-ID 1906.11471, Seite 1-7 |
Abstract: | Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly inapplicable to active learning. Within the standardized workflow, the acquisition function is chosen among available heuristics a priori, and its success is observed only after the labeling budget is already exhausted. More importantly, none of the earlier studies report a unique consistently successful acquisition heuristic to the extent to stand out as the unique best choice. We present a method to break this vicious circle by defining the acquisition function as a learning predictor and training it by reinforcement feedback collected from each labeling round. As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution. Our system consists of a Bayesian neural net, the predictor, a bootstrap acquisition function, a probabilistic state definition, and another Bayesian policy network that can effectively incorporate this input distribution. We observe on three benchmark data sets that our method always manages to either invent a new superior acquisition function or to adapt itself to the a priori unknown best performing heuristic for each specific data set. |
DOI: | doi:10.48550/arXiv.1906.11471 |
URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
Volltext ; Verlag: https://doi.org/10.48550/arXiv.1906.11471 |
| Volltext: http://arxiv.org/abs/1906.11471 |
| DOI: https://doi.org/10.48550/arXiv.1906.11471 |
Datenträger: | Online-Ressource |
Sprache: | eng |
Sach-SW: | Computer Science - Machine Learning |
| Statistics - Machine Learning |
K10plus-PPN: | 1810087864 |
Verknüpfungen: | → Sammelwerk |
Deep active learning with adaptive acquisition / Haußmann, Manuel [VerfasserIn]; 27 Jun 2019 (Online-Ressource)
68941151