(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Termin in Kalender importieren: iCal (Download)
Vorträge
| Vortragende(r)
|
Huijie Wang
|
| Titel
|
Predictability of Classfication Performance Measures with Meta-Learning
|
| Vortragstyp
|
Bachelorarbeit
|
| Betreuer(in)
|
Jakob Bach
|
| Vortragssprache
|
|
| Vortragsmodus
|
|
| Kurzfassung
|
Choosing a suitable classifier for a given dataset is an important part in the process of solving a classification problem. Meta-learning, which learns about the learning algorithms themselves, can predict the performance of a classifier without training it. The effect of different types of performance measures remains unclear, as it is hard to draw a comparison between results of existing works, which are based on different meta-datasets as well as meta-models. In this thesis, we study the predictability of different classification performance measures with meta-learning, also we compare the performances of meta-learning using different meta-regression models. We conduct experiments with meta-datasets from previous studies considering 11 meta-targets and 6 meta-models. Additionally, we study the relation between different groups of meta-features and the performance of meta-learning. Results of our experiments show that meta-targets have similar predictability and the choice of meta-model has a big impact on the performance of meta-learning.
|
- Neuen Vortrag erstellen
Hinweise
