Details
| Original language | German |
|---|---|
| Number of pages | 8 |
| Publication status | Published - Jul 2018 |
| Externally published | Yes |
| Event | International Workshop on Automatic Machine Learning 2018 - Stockholm, Sweden Duration: 14 Jul 2018 → 14 Jul 2018 |
Workshop
| Workshop | International Workshop on Automatic Machine Learning 2018 |
|---|---|
| Abbreviated title | ICML 2018 AutoML Workshop |
| Country/Territory | Sweden |
| City | Stockholm |
| Period | 14 Jul 2018 → 14 Jul 2018 |
Abstract
from performance issues when dealing with larger datasets. In this paper, we present an alternative approach leveraging a hierarchical planning to configure machine learning pipelines that are unlimited in length. We evaluate our approach and find its performance to be competitive with other AutoML tools, including TPOT.
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2018. Paper presented at International Workshop on Automatic Machine Learning 2018, Stockholm, Sweden.
Research output: Contribution to conference › Paper › Research › peer review
}
TY - CONF
T1 - ML-Plan for Unlimited-Length Machine Learning Pipelines
AU - Wever, Marcel
AU - Mohr, Felix
AU - Hüllermeier, Eyke
PY - 2018/7
Y1 - 2018/7
N2 - In automated machine learning (AutoML), the process of engineering machine learning applications with respect to a specific problem is (partially) automated. Various AutoML tools have already been introduced to provide out-of-the-box machine learning functionality. More specifically, by selecting machine learning algorithms and optimizing their hyperparameters, these tools produce a machine learning pipeline tailored to the problem at hand. Except for TPOT, all of these tools restrict the maximum number of processing steps of such a pipeline. However, as TPOT follows an evolutionary approach, it suffersfrom performance issues when dealing with larger datasets. In this paper, we present an alternative approach leveraging a hierarchical planning to configure machine learning pipelines that are unlimited in length. We evaluate our approach and find its performance to be competitive with other AutoML tools, including TPOT.
AB - In automated machine learning (AutoML), the process of engineering machine learning applications with respect to a specific problem is (partially) automated. Various AutoML tools have already been introduced to provide out-of-the-box machine learning functionality. More specifically, by selecting machine learning algorithms and optimizing their hyperparameters, these tools produce a machine learning pipeline tailored to the problem at hand. Except for TPOT, all of these tools restrict the maximum number of processing steps of such a pipeline. However, as TPOT follows an evolutionary approach, it suffersfrom performance issues when dealing with larger datasets. In this paper, we present an alternative approach leveraging a hierarchical planning to configure machine learning pipelines that are unlimited in length. We evaluate our approach and find its performance to be competitive with other AutoML tools, including TPOT.
M3 - Paper
T2 - International Workshop on Automatic Machine Learning 2018
Y2 - 14 July 2018 through 14 July 2018
ER -