• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

News

Our colleagues Alexander Shekhovtsov representing Czech Technical University in Prague and Belhal Karimi representing Ecole Polytechnique & INRIA gave talks on actual problems of machine learning

24 of July Alexander Shekhovtsov (Czech Technical University in Prague), invited by the Centre of Deep Learning and Bayesian Methods, and Belhal Karimi (Ecole Polytechnique & INRIA), a summer intern of the Centre, made presentations at the Faculty of Computer Science

Our colleagues Alexander Shekhovtsov representing Czech Technical University in Prague and Belhal Karimi representing Ecole Polytechnique & INRIA gave talks on actual problems of machine learning

Our colleagues gave talks on actual problems of machine learning.

Alexander Shekhovtsov (Czech Technical University in Prague) presented a talk entitled "Statistical Problems in Neural Networks". 
Neural Networks (NNs) have become a very well working technology, in fact so well that it seemingly obviates the need for statistical models and statistical decision theory.
In this talk Alexander highlighted different aspects of Neural Networks that require statistical treatment, discuss open problems and our modest contribution towards addressing them.

Belhal Karimi (Ecole Polytechnique & INRIA) emphasized in his report "Nonconvex Optimization for Latent Data Models: An Incremental and An Online Point of View" that recent breakthroughs in statistical modeling, such as deep learning, coupled with an explosion of data samples, require improvements of nonconvex optimization procedures for large datasets.
This talk has become an attempt to address those two challenges by developing algorithms with cheaper updates, ideally independent of the number of samples, and improving the theoretical understanding of nonconvex optimization that remains rather limited.