Gatsby Unit Seminars

External seminar series of the Gatsby Computational Neuroscience Unit. See here for more information.
Contact: Yee Whye Teh

Usual time: Wednesday, 16:00 - 17:00
Location (unless otherwise noted): B10, Alexandra House
iCalendar URL: www.csml.ac.uk/ics/series/1

Upcoming Events

No events found.

Previous Events

DateDescription
Wed, 20 Feb 2013 Zoubin Ghahramani (University of Cambridge): Bayesian nonparametric modelling of networks
Wed, 30 Jan 2013 Neil Lawrence (University of Sheffield): Deep Gaussian Processes
Wed, 28 Nov 2012 Charles Sutton (University of Edinburgh): Quasi-Newton Methods and Continuous Relaxations for MCMC
Wed, 14 Nov 2012 Wicher Bergsma (LSE): Nonparametric testing of conditional independence
Wed, 31 Oct 2012 Roger Grosse (MIT): Model selection in a large compositional space
Tue, 03 Jul 2012 Inderjit S. Dhillon (The University of Texas at Austin): Fast Coordinate Descent Methods with Variable Selection for Non-negative Matrix Factorization
Mon, 02 Jul 2012 Yoshua Bengio (University of Montreal): Sampling from Auto-Encoders performing Manifold Learning and Implicit Density Estimation
Fri, 22 Jun 2012 Steven C.H. Hoi (Nanyang Technological University): Online Learning for Mining Big Media Data
Wed, 23 May 2012 Marc Toussaint (FU Berlin): Optimal control and model-free Reinforcement Learning as KL minimization
Wed, 11 Apr 2012 Bert Kappen (Radboud University Nijmegen): Path Integral Reinforcement Learning
Mon, 02 Apr 2012 Zaid Harchaoui (INRIA Rhone-Alpes): Learning with matrix gauge regularization penalty
Wed, 14 Mar 2012 Iain Murray (University of Edinburgh): Sampling hierarchical latent Gaussian models
Mon, 12 Mar 2012 Lorenzo Rosasco (Massachusetts Institute of Technology and Istituto Italiano di Tecnologia): Learning Functions and (Data) Sets with Spectral Regularization
Wed, 29 Feb 2012 Sumeettpal Singh (University of Cambridge): Parameter Estimation for Hidden Markov Models with Intractable Likelihoods
Wed, 22 Feb 2012 Vikash Mansinghka (MIT): How to be stochastic about probabilistic programming, and why it is worth the trouble
Wed, 15 Feb 2012 Danny Bickson (Carnegie Mellon University): Large scale iterative computation using GraphLab