- This event has passed.
TECoSA Course Module “Machine Reasoning Explainability (an AAMAS tutorial)”
March 9, 2022, 09:00 – 12:30
Attendance is free to all TECoSA members. To register, please email email@example.com stating which module(s) you wish to take. Alternatively, calendar invitations will be issued to everyone on the tecosa-all mailing list. You can register by accepting the invitations that are of interest to you.
Format: One 3.5-hour tutorial
Location: Online (via Teams)
Timing: Weds 9 March kl.9-12.30 CET
Module lead by: Ericsson: Alexandros Nikou, Kristijonas Cyras, Swarup Kumar Mohalik, Alessandro Previti (with support from Anusha Pradeep Mujumdar and Aneta Vulgarakis Feljan)
Content: *Concept; *Technical Part 1(Inference-Based Explanations; SAT/SMT Analysis of Inconsistencies; Argumentation-Based Explanations); *Technical Part 2 (Explainable Planning; Symbolic RL, Explainability; Causal Approaches to Explainability); *Conclusions.
Abstract: As a field of AI, Machine Reasoning (MR) uses largely symbolic means to formalize and emulate abstract reasoning. Studies in early MR have notably started inquiries into Explainable AI (XAI) – arguably one of the biggest concerns today for the AI community. Work on explainable MR as well as on MR approaches to explainability in other areas of AI has continued ever since. It is especially potent in modern MR branches such as argumentation, constraint and logic programming, and planning. We hereby aim to provide a selective overview of MR explainability techniques and studies in hopes that insights from this long track of research will complement well the current XAI landscape.