Semantische Suche
Freitag, 10. Juli 2020, 11:30 Uhr
iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: {{{Webkonferenzraum}}}
(Keine Vorträge)
Freitag, 17. Juli 2020, 11:30 Uhr
iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: {{{Webkonferenzraum}}}
| Vortragende(r) | Daniel Betsche |
|---|---|
| Titel | Feature-Based Time Series Generation |
| Vortragstyp | Masterarbeit |
| Betreuer(in) | Adrian Englhardt |
| Vortragsmodus | |
| Kurzfassung | To build highly accurate and robust machine learning algorithms practitioners require data in high quality, quantity and diversity. Available time series data sets often lack in at least one of these attributes. In cases where collecting more data is not possible or too expensive, data-generating methods help to extend existing data. Generation methods are challenged to add diversity to existing data while providing control to the user over what type of data is generated. Modern methods only address one of these challenges. In this thesis we propose a novel generation algorithm that relies on characteristics of time series to enable control over the generation process. We combine classic interpretable features with unsupervised representation learning by modern neural network architectures. Further we propose a measure and visualization for diversity in time series data sets. We show that our approach can create a controlled set of time series as well as adding diversity by recombining characteristics across available instances. |
Freitag, 24. Juli 2020, 11:30 Uhr
iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: {{{Webkonferenzraum}}}
(Keine Vorträge)
Freitag, 24. Juli 2020, 14:00 Uhr
iCal (Download)
Webkonferenz: {{{Webkonferenzraum}}}
| Vortragende(r) | Sebastian Hahner |
|---|---|
| Titel | Domain-specific Language for Data-driven Design Time Analyses and Result Mappings for Logic Programs |
| Vortragstyp | Masterarbeit |
| Betreuer(in) | Stephan Seifermann |
| Vortragsmodus | |
| Kurzfassung | In today's connected world, exchanging data is essential to many business applications. In order to cope with security requirements early, design time data flow analyses have been proposed. These approaches transform the modeled architecture into underlying formalisms such as logic programs. Constraints that check requirements often have to be formulated in terms of the underlying formalism. This requires architects to know about the formalism, the transformed architecture and the verification environment. We aim to bridge this gap between the architectural domain and the underlying formalism. We propose a domain-specific language (DSL) which enables architects to define individual constraints in terms of the architecture. Our approach maps the constraints and results between the architectural and the formalism automatically. Our evaluation indicates good overall expressiveness, usability and space efficiency for different sized data flow restrictions. |
Freitag, 14. August 2020, 11:30 Uhr
iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: {{{Webkonferenzraum}}}
| Vortragende(r) | Cem Özcan |
|---|---|
| Titel | Meta-Learning for Feature Importance |
| Vortragstyp | Bachelorarbeit |
| Betreuer(in) | Jakob Bach |
| Vortragsmodus | |
| Kurzfassung | Feature selection is essential to the field of machine learning, since its application results in an enhancement in training time as well as prediction error of machine learning models. The main problem of feature selection algorithms is their reliance on feature importance estimation, which requires the training of models and is therefore expensive computationally. To overcome this issue, we propose MetaLFI, a meta-learning system that predicts feature importance for classification tasks prior to model training: We design and implement MetaLFI by interpreting feature importance estimation as a regression task, where meta-models are trained on meta-data sets to predict feature importance for unseen classification tasks. MetaLFI calculates a meta-data set by characterizing base features using meta-features and quantifying their respective importance using model-agnostic feature importance measures as meta-targets. We evaluate our approach using 28 real-world data sets in order to answer essential research questions concerning the effectiveness of proposed meta-features and the predictability of meta-targets. Additionally, we compare feature rankings put out by MetaLFI to other feature ranking methods, by using them as feature selection methods. Based on our evaluation results, we conclude that the prediction of feature importance is a computationally cheap alternative for model-agnostic feature importance measures. |