A workshop of the ECMI Special Interest group Mathematics for Big Data and Artificial Intelligence
Organized by Alessandra Micheletti (Univ. of Milan), Nataša Krejić (Univ. of Novi Sad) and Diana Manvelyan (SIEMENS AG)
https://sites.google.com/view/ecmi-xai/home
October 14, 2024, Siemens Garching Campus (Munich, Germany)
The recent surge of Machine Learning (ML) and, more broadly, of Artificial Intelligence (AI) brings to light old and new open issues, and among them, the so-called eXplainable Artificial Intelligence (XAI) – AI that humans can understand.
AI has recently seen a significant shift in focus towards designing and developing intelligent systems that are interpretable, transparent and explainable. This is due to the complexity of the induced model from data and the legal requirement imposed by various national and international parliaments. Consequently, this has echoed in the research literature and the press, attracting scholars worldwide and a lay audience. In particular, XAI can help solve some of the problems of AI, as highlighted in the Regulation of the European Parliament and The Council (AI ACT), laying down harmonised rules on Artificial Intelligence and amending certain union legislative acts.
The aim of this workshop is to discuss possibilities for designing XAI methods and its industrial applications, focussing on the emerging and fundamental role played by Mathematics in this area.
Mathematical methods which promise to improve the explainability of AI include (but are not limited to) Computational Geometry, Topological Data Analysis, Group Equivariant Non- Expansive Operators (GENEOs), Physics Informed Neural Networks (PINNs), measures of robustness, regularisation methods to reduce computational complexity, distributed and federated optimization.
During the workshop a sequence of topics that deal with both theoretical and practical aspects of the above-mentioned mathematical techniques will be presented and discussed.
A number of relevant industrial case studies, also enhancing the main related open problems, will also be presented.
The workshop will consist of one session where 5 talks will be presented, followed by a round table on different perspectives for AI. The tentative schedule is as follows
12:00 – 13:00 – light lunch
13:00 – 16:00 – Plenary Session
13:00-13:15 Natasa Krejic and Alessandra Micheletti: Opening and presentation of the ECMI Special Interest group “Mathematics for Big Data and AI”
13:15-13:30 Diana Manvelyan: Enabling Digital Twins using AI: Industrial Mathematics Perspective
13:30-14:00 Georgios Bouloukakis: Enabling Trustworthy Datasets for Efficient AIoT Operation
14:00-14:30 Giuseppe Primiero: Bias identification and mitigation in opaque computational systems with BRIO
14:30 – 15:00 Claudia Soares: Advancing Solutions for the Three-Body Problem Through Physics-Informed Neural Networks
15:00 – 15:30 Manuel Pio Silva: Energy cases where XAI can make a difference
15:30 – 16:00 Patrizio Frosini: Group Equivariant Non Expansive Operators (GENEOs) as geometric instruments to build transparent and robust AI models
16:00 – 16:30 – coffee break
16:30 – 18:00 – Round table: Different perspectives for AI
There are no participation fees but the registration is mandatory to participate.
The registration form is available here:
https://forms.gle/csgaz6mhj8dc5R579
The workshop will be followed by the workshop Advancing Scientific Machine Learning in Industry
organized by Wil Schilders (TUM-IAS), Dirk Hartmann (Siemens) during October 15-16, 2024 and you are welcome to participate at both events. The announcement and registration for the second workshop can be found here: https://www.ias.tum.de/ias/research-areas/advanced-computation-and-modeling/scientific-machine-learning/