Machine-learning-nederland July 2024

machine-learning-nederland@list.uva.nl

2 participants
2 discussions

Fwd: [TIAI-seminar] Sanjoy Dasgupta, July 11
by Tim van Erven 11 Jul '24

11 Jul '24

Dear all, There is an online seminar today by Sanjoy Dasgupta <https://cseweb.ucsd.edu/~dasgupta/> at 15.00, which may be of broader interest. Sanjoy is internationally well known for his work on clustering and unsupervised learning, and has a reputation as an excellent speaker. His talk today will be about new results on interpretable clustering. See below for details. This is part of a new online seminar about Theory for Interpretable AI. For further seminar info, see tverven.github.io/tiai-seminar/ <http://tverven.github.io/tiai-seminar/> Best, Tim -------- Forwarded Message -------- Subject: [TIAI-seminar] Sanjoy Dasgupta, July 11 Date: Fri, 5 Jul 2024 21:37:36 +0300 From: Michal Moshkovitz via TIAI-seminar <tiai-seminar(a)list.uva.nl> Reply-To: Michal Moshkovitz <michal.moshkovitz(a)mail.huji.ac.il> To: tiai-seminar(a)list.uva.nl Dear all, Unsupervised learning is a significant branch of machine learning, with k-means clustering being a key subproblem. However, it often lacks interpretability. Can we make it interpretable? Apparently we can. On this topic, our next speaker in the Theory of Interpretable AI Seminar, Sanjoy Dasgupta, will review recent progress on interpretable k-means clustering. *Speaker*: Sanjoy Dasgupta <https://cseweb.ucsd.edu/~dasgupta/> *Date*: Thursday, July 11, 15.00 Central European Time (CET) / 9.00 am Eastern Standard Time (EST) *Zoom link*:https://uva-live.zoom.us/j/87120549999 *Title*: Recent progress on interpretable clustering The widely-used k-means procedure returns k clusters that have arbitrary convex shapes. In high dimension, such a clustering might not be easy to understand. A more interpretable alternative is to constrain the clusters to be the leaves of a decision tree with axis-parallel splits; then each cluster is a hyper-rectangle given by a small number of features. Is it always possible to find clusterings that are interpretable in this sense and yet have k-means cost that is close to the unconstrained optimum? A recent line of work has answered this in the affirmative and moreover shown that these interpretable clusterings are easy to construct. I will give a survey of these results: algorithms, methods of analysis, and open problems. *General Seminar info*: Web:tverven.github.io/tiai-seminar/ <http://tverven.github.io/tiai-seminar/> Google calendar:Google calendar<https://calendar.google.com/calendar/u/1?cid=NTlhNjNhZDQ5ZmUxYmM5MmRmZTMwNz…> *Upcoming speakers*: - September 5: Lesia Semenova - October 10: Ulrike von Luxburg Best Regards, Michal Moshkovitz Also on behalf of TIAI co-organizers Suraj Srinivas and Tim van Erven

1 0

Call for online participation: IAS Workshop on Logic and AI (July 16-17, 2024)
by Balder ten Cate 10 Jul '24

10 Jul '24

*Workshop on Logic and AI* *July 16-17, 2024* *Amsterdam Institute for Advanced Study (IAS)* This workshop is part of an IAS research project on the topic of “Logic and AI”. It will bring together international experts to explore the promising interaction of logic and modern artificial intelligence (AI). While AI struggles with explainability, interpretability, and verifiability, logic excels at this. So can logic help AI? And if so, how? The workshop has sessions on expressive and computational power of machine learning, neuro-symbolic integration, and causality, logic, and machine learning. Speakers include Giuseppe Marra (KU Leuven), Levin Hornischer (LMU Munich), Martin Grohe (RWTH Aachen), Lena Strobl (Umeå University), Herbert Jaeger (University of Groningen), Atticus Geiger (Pr(Ai)²R), Thomas Icard (Stanford University). Due to limited space, on-site participation is by invitation, but the talks can be followed online. If you would like to follow the talks online, please submit the registration form indicating online participation and you will receive a Zoom link. For more information, see: https://ias.uva.nl/content/events/2024/07/logic-and-ai.html

1 0

2024

2023

2022

2021

2020

Machine-learning-nederland July 2024