San Francisco, California
London, United Kingdom
* THE MONDAY MASTERCLASS HAS BEEN SOLD OUT, BUT PLEASE REMEMBER THAT THE EVENTS ON TUESDAY AND WEDNESDAY DO NOT REQUIRE PRE-REGISTRATION *
Deep learning methods have been extremely successful recently, in particular in the areas of speech recognition, object recognition and language modeling. Deep representations are representations at multiple levels of abstraction, of increasing non-linearity. The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation-learning algorithms implementing such priors. This talk introduces basic concepts in representation learning, distributed representations, and deep learning, both supervised and unsupervised.
This is the first of three talks. Two Distinguished Lectures will take place, on 22nd and 23rd of October, same time and location.
Tuesday 22 October 2013
Lunch will follow each lecture, in the Pearson Reading Room in the same building.
There is no need to sign up for the Tuesday and Wednesday talks. For more information please see: http://www.csml.ucl.ac.uk/events/master_classes
Sponsored by DeepMind Technologies: an ambitious London-based startup building general-pupose learning algorithms, with initial product applications in mobile social gaming.
When & Where
The Centre for Computational Statistics and Machine Learning (CSML) spans three departments at University College London, Computer Science, Statistical Science, and the Gatsby Computational Neuroscience Unit. The Centre will pioneer an emerging field that brings together statistics, the recent extensive advances in theoretically well-founded machine learning, and links with a broad range of application areas drawn from across the college, including neuroscience, astrophysics, biological sciences, complexity science, etc. There is a deliberate intention to maintain and cultivate a plurality of approaches within the centre including Bayesian, frequentist, on-line, statistical, etc.