Institutsseminar/2020-06-05

Aus SDQ-Institutsseminar
Die druckbare Version wird nicht mehr unterstützt und kann Darstellungsfehler aufweisen. Bitte aktualisiere deine Browser-Lesezeichen und verwende stattdessen die Standard-Druckfunktion des Browsers.
Termin (Alle Termine)
Datum Freitag, 5. Juni 2020
Uhrzeit 11:30 – 13:00 Uhr (Dauer: 90 min)
Ort Raum 348 (Gebäude 50.34)
Webkonferenz
Vorheriger Termin Fr 29. Mai 2020
Nächster Termin Fr 5. Juni 2020

Termin in Kalender importieren: iCal (Download)

Vorträge

Vortragende(r) Moritz Renftle
Titel Assessing Human Understanding of Machine Learning Models
Vortragstyp Masterarbeit
Betreuer(in) Holger Trittenbach
Vortragsmodus
Kurzfassung To deploy an ML model in practice, a stakeholder needs to understand the behaviour and implications of this model. To help stakeholders develop this understanding, researchers propose a variety of technical approaches, so called eXplainable Artificial Intelligence (XAI). Current XAI approaches follow very task- or model-specific objectives. There is currently no consensus on a generic method to evaluate most of these technical solutions. This complicates comparing different XAI approaches and choosing an appropriate solution in practice. To address this problem, we formally define two generic experiments to measure human understanding of ML models. From these definitions we derive two technical strategies to improve understanding, namely (1) training a surrogate model and (2) translating inputs and outputs to effectively perceivable features. We think that most existing XAI approaches only focus on the first strategy. Moreover, we show that established methods to train ML models can also help stakeholders to better understand ML models. In particular, they help to mitigate cognitive biases. In a case study, we demonstrate that our experiments are practically feasible and useful. We suggest that future research on XAI should use our experiments as a template to design and evaluate technical solutions that actually improve human understanding.
Vortragende(r) Alan Mazankiewicz
Titel Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization
Vortragstyp Masterarbeit
Betreuer(in) Klemens Böhm
Vortragsmodus
Kurzfassung Human Activity Recognition (HAR) from accelerometers is a fundamental problem in ubiquitous computing. Machine learning based recognition models often perform poorly when applied to new users that were not part of the training data. Previous work has addressed this challenge by personalizing general recognition models to the motion pattern of a new user in a static batch setting. The more challenging online setting has received less attention. No samples from the target user are available in advance, but they arrive sequentially. Additionally, the user's motion pattern may change over time. Thus, adapting to new and forgetting old information must be traded off. Finally, the target user should not have to do any work to use the recognition system by labeling activities. Our work addresses this challenges by proposing an unsupervised online domain adaptation algorithm. It works by aligning the feature distribution of all the subjects, sources and target, within deep neural network layers.
Neuen Vortrag erstellen

Hinweise