Efficient Machine Learning with High Order and Combinatorial Structures

Add to your list(s) Download to your calendar using vCal

• Danny Tarlow
• Thursday 05 April 2012, 09:30-10:30
• Large lecture theatre, Microsoft Research Ltd, 7 J J Thomson Avenue (Off Madingley Road), Cambridge.

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

o This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attendin

Two challenges facing machine learning researchers are (a) how to build models that more accurately reflect prior beliefs and constraints relevant to the domain being modeled, and (b) how to model more complexly structured data. In both of these cases, there are tradeoffs between the expressibility of the model and the computational efficiency of learning and inference procedures. In this talk, I will discuss several recent approaches towards building more expressive and more efficient models of structured domains. The focus will be on learning and inference procedures for models that have non-local (high order) and/or combinatorial structure.

This talk is part of the Microsoft Research Cambridge, public talks series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Guy Emerson's list
• Interested Talks
• Large lecture theatre, Microsoft Research Ltd, 7 J J Thomson Avenue (Off Madingley Road), Cambridge
• Microsoft Research Cambridge, public talks
• Optics for the Cloud
• PMRFPS's
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• personal list
• rp587

Note that ex-directory lists are not shown.