We are happy to announce that our next Coffee Seminar will take place virtually on April 7th 2022 (9:30-10:30am) with Johannes Fürnkranz as an invited speaker.
Johannes is a professor at the Johannes Kepler University in Linz**.** He will present his work titled — Towards Deep and Interpretable Rule Learning — see abstract below.
The speaker of the seminar will be virtual and the seminar will broadcasted on the following webex link: https://ibm.webex.com/meet/france.research.team
Everyone from the Saclay/Paris area is invited to join us on site for a coffee starting at 9am and we will watch the seminar is a seminar room (5th floor, IBM France Lab, Rue Alfred Kastler, 91400 Orsay, France). Please drop us an email in case you want to attend in person.
We would greatly appreciate if you could broadcast this message within your team/organization. Note that if they want to subscribe they have to send “subscribe” to france.research.team@ibm.com
Kind regards,
Remy Kusters and Maxence Ernoult
on behalf of IBM Research Paris/Saclay
Title: Towards Deep and Interpretable Rule Learning
Abstract : Inductive rule learning is concerned with the learning of classification rules from data. Learned rules are inherently interpretable and easy to implement, so they are very suitable for formulating learned models in many domains. Nevertheless, current rule learning algorithms have several shortcomings. First, we argue that longer rules are often more interpretable than shorter rules, and that the tendency of current rule learning algorithms to strive for short and concise rules should be replaced with alternative methods that allow for longer concept descriptions. Second, we think that the main impediment of current rule learning algorithms is that they are not able to learn deeply structured rule sets, unlike the successful deep learning techniques. Both points are currently under investigation in our group, and we will show some preliminary results.
#GlobalDataScience