UM Data Science Research Seminar
The UM Data Science Research Seminar Series are monthly sessions organised by the Institute of Data Science, on behalf of the UM Data Science Community, in collaboration with different departments across UM with the aim to bring together data scientists from Maastricht University to discuss breakthroughs and research topics related to Data Science.
This session is organised in collaboration with the Department of Data Science and Knowledge Engineering (DKE)
Time: 12:00 - 12:30
Title: Explainable AI is not yet understandable AI.
Speaker: Prof. Nava Tintarev
Abstract: Decision-making at individual, business, and societal levels is influenced by online content. Filtering and ranking algorithms such as those used in recommender systems are used to support these decisions. However, it is often not clear to a user whether the advice given is suitable to be followed, e.g., whether it is correct, whether the right information was taken into account, or if the user’s best interests were taken into consideration. In other words, there is a large mismatch between the representation of the advice by the system versus the representation assumed by its users.
This talk addresses why we (might) want to develop advice-giving systems that can explain themselves, and how we can assess whether we are successful in this endeavor. This talk will also describe some of the state-of-the-art in explanations in a number of domains (music, tweets, and news articles) that help link the mental models of systems and people. However, it is not enough to generate rich and complex explanations; more is required in order to understand and be understood. This entails among other factors decisions around which information to select to show to people, and how to present that information, often depending on the target users and contextual factors.
Time: 12:30 - 13:00
Title: Unraveling information in signals: the hunt for frequency information.
Speaker: Dr. Joël Karel
Abstract: For numerous applications, it is important to know which frequencies occur when, and how the frequency content of a signal varies over time. This requires to generate a time-frequency representation of a signal. However, many of these methods make assumptions about the data such as stationarity or linearity. Approaches like the short-term Fourier transforms allow to handle non-stationary data, but they are limited by a trade-off in the resolution they can achieve in both time and frequency simultaneously. Empirical, aka data driven, techniques can be used for non-stationary and non-linear data, and help address the above trade-off.
At the Department of Data Science and Knowledge Engineering we perform research in time-frequency representations. In this presentation we will cover a number of these techniques such as wavelet decompositions and singular spectrum decomposition.