Last Seminar
Efficient Low-Dimensional Compression for Deep Overparameterized Learning
Tuesday, 4 June 13:00 - 14:00 WET
Abstract:
Healthcare research has changed dramatically in the last decade. From the development of top algorithms for patient diagnosis and profiling, including the recent advances on chatbots such as Med-Gemini, to the public release of increasingly larger and more challenging medical datasets, it is undeniable that we are living an exciting era for those working in the interface between machine learning and healthcare. However, working on safety critical applications brings an additional level of responsibility. Here, a prediction error may have dire consequences, as we often work with life or death situations. Thus, it becomes critical to understand our models, their decisions and failure modes. Moreover, this understanding should be grounded on the actual knowledge and needs of those that will work with the models: doctors, patients, insurance companies, or even the developers. In this talk I will present an overview of our path towards the development of healthcare models for cancer analysis. This path has followed two core ideas: i) human expectations and knowledge must be integrated in the model development; and ii) we must be able to understand the model decisions. This has led to the proposal of several approaches that combine a human-centered vision with the concept of explainable AI.
Register here on EventBrite.
The Priberam Machine Learning Lunch Seminars are a series of informal meetings which occur every two weeks at Instituto Superior Técnico, in Lisbon. It works as a discussion forum involving different research groups, from IST and elsewhere. Its participants are interested in areas such as (but not limited to): statistical machine learning, signal processing, pattern recognition, computer vision, natural language processing, computational biology, neural networks, control systems, reinforcement learning, or anything related (even if vaguely) with machine learning.
The seminars last for about one hour (including time for discussion and questions) and revolve around the general topic of Machine Learning. The speaker is a volunteer who decides the topic of his/her presentation. Past seminars have included presentations about state-of-the-art research, surveys and tutorials, practicing a conference talk, presenting a challenging problem and asking for help, and illustrating an interesting application of Machine Learning such as a prototype or finished product.
Presenters can have any background: undergrads, graduate students, academic researchers, company staff, etc. Anyone is welcome both to attend the seminar as well as to present it. Occasionally we will have invited speakers. Browse the archive (on the left) for a list of all past seminars, including the speakers, titles, abstracts and, whenever possible, the video and/or slides from the presentation.
Note: The seminars are held at lunch-time, and include delicious free food.
Feel free to join our mailing list, where seminar topics are announced beforehand. You may also visit the group webpage. Anyone can attend the seminars. If you would like to present something, please send us an email.
The seminars were usually held every other Tuesday, from 1 PM to 2 PM, at the IST campus in Alameda. This sometimes changes due to availability of the speakers, so check regularly! Since 2020, due to the pandemic, they have been taking place online, via Zoom.
The 2020-2021 season is now over. We will come back soon for a new season. Meanwhile please check some of the last seminars in Priberam’s YouTube channel.