REMINDER Invitation to the ICTP Colloquium by Prof. John S. Shawe-Taylor, on "Statistical Learning Theory for Modern Machine Learning" on Friday 22 September 2023 at 1400 hrs, BLH

[Infopoint]

Dear All,

You are most cordially invited to the ICTP Colloquium by Prof. John S. 
Shawe-Taylor, University College London, on "Statistical Learning Theory 
for Modern Machine Learning".

*The Colloquium will take place (in presence) on Friday 22 September 
2023 at 14:00 hrs in the Budinich Lecture Hall.*

*Biosketch: *John S Shawe-Taylor is a professor at University College 
London (UK) and Director of the Centre for Computational Statistics and 
Machine Learning at UCL. His main research area is Statistical Learning 
Theory. His contributions range from Neural Networks, to Machine 
Learning, to Graph Theory.  He has coordinated a number of European wide 
projects investigating the theory and practice of Machine Learning, 
including the NeuroCOLT projects. He is currently the scientific 
coordinator of a Framework VI Network of Excellence in Pattern Analysis, 
Statistical Modelling and Computational Learning (PASCAL) involving 57 
partners and director of IRCAI, a UNESCO category 2 Institute on 
artificial intelligence based in Ljubljana

*Abstract:* Machine learning aims to identify properties of a 
distribution from a set of examples. The presentation introduces the 
statistical learning framework for analysing this task, focussing on the 
PAC-Bayes approach that draws on Bayesian inference and Probably 
Approximately Correct learning. The application of this analysis to 
modern machine learning approaches including Kernel methods and deep 
learning will be presented, highlighting successes and ongoing 
shortcomings of these results.

More information can be found at the following link: 
https://indico.ictp.it/event/10444

The Colloquium will be livestreamed on www.ictp.it/livestream

Light refreshments will be served on the Leonardo Building Terrace at 
the end of the talk.

Looking forward to your participation.

With best regards,

Director's Office, ICTP

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.ictp.it/pipermail/ictp-announcements/attachments/20230920/2119c54b/attachment.htm>