Our Talks

Reliable Diagnostics by Conformal Predictors

  • Prof. Alex Gammerman
  • October 2015
  • Berlin, Germany

The talk reviews a modern machine learning technique called Conformal Predictors.

The talk outlines the basic ideas of Conformal Predictors and then illustrates the technique with applications to several medical problems.

Large-scale Probabilistic Prediction With and Without Validity Guarantees

  • Prof. Vladimir Vovk
  • October 2015
  • Berlin, Germany

The topic of this talk is a method of turning machine-learning algorithms into probabilistic predictors that automatically enjoys a property of validity, is computationally efficient, and preserves predictive efficiency.

Intelligent Learning: Similarity Control and Knowledge Transfer

  • Prof. Vladimir Vapnik
  • October 2015
  • Berlin, Germany

The common observation was that human students require much less examples for training than a learning machine. It is because the human students have an intelligent teacher and that teacher-student interactions are based not only on the brute force methods of function estimation from observations.

Treatment of Uncertainty in the Foundations of Probability

  • Prof. Vladimir Vovk
  • December 2016
  • New Jersey, USA

Game-theoretic probability formalizes the picture in which both risk and uncertainty interfere at every moment. The fruitfulness of this picture will be demonstrated by open theories in science and the emergence of stochasticity and probability in finance.

​Brute Force and ​Intelligent ​Methods of Learning

  • Prof. Vladimir Vapnik
  • May 2016
  • California, USA

The goal of this talk is to introduce a new conceptual model of learning, the so-called Intelligent Learning, which goes beyond the classical model.

​Rethinking Statistical Learning Theory: Learning Using Statistical Invariants

  • Prof. Vladimir Vapnik
  • June 2018
  • The Netherlands

In the talk I will consider Teacher-Student interaction in learning processes. I will introduce a new learning paradigm, called Learning Using Statistical Invariants (LUSI), which is different from the classical one.

Commemorative Talks in memory of Alexey Chervonenkis

  • Prof. Anatoly Michalsky
  • September 2015
  • Egham, United Kingdom

This talks summarises the applications of data analysis and machine learning, developed by Alexey Chervonenkis.

Randomness and Non-determinism

  • Prof. Leonid Levin
  • September 2004
  • Egham, United Kingdom

This talk was delivered by Prof. Leonid Levin for the Kolmogorov Lecture 2004.

The Universal Distribution and Machine Learning

  • Prof. Ray Solomonoff
  • September 2003
  • Egham, United Kingdom

This talk was delivered by Prof. Ray Solomonoff for the Kolmogorov Lecture 2003.

Memorial Concert Celebrating the Life of Alexey Chervonenkis

  • Royal Holloway Chapel
  • September 2015
  • Egham, United Kingdom

This concert was presented to celebrate the life of Alexey Chervonenkis

Similarity Control and Knowledge Transfer

  • Prof. Vladimir Vapnik
  • September 2015
  • Egham, United Kingdom

This talk was delivered by Prof. Vladimir Vapnik at SLDS 2015 conference.