[talks] Colloquium- David Duvenaud, Thursday, Feb 18th, 12:30pm

[Mitra Kelly]

Colloquium Speaker

David Duvenaud

thursday, Feb 18th, 12:30pm

CS 105

 

Talk title: Composing differentiable procedures for modeling, inference, and
optimization

Talk abstract: Much recent success in machine learning has been through
optimizing simple feedforward procedures, such as neural networks, using
gradients.  Surprisingly, many complex procedures such as message passing,
filtering, inference, and even optimization itself can be meaningfully
differentiated though as well.  Composing these procedures lets us build
sophisticated models that generalize existing methods but retain their good
properties.  We'll show applications to chemical design, gradient-based
tuning of optimization procedures, and training procedures that don't
require cross-validation.

Bio: David Duvenaud is a postdoc in the Harvard Intelligent Probabilistic
Systems group, working with Prof. Ryan Adams on model-based optimization,
synthetic chemistry, and neural networks.  He did his Ph.D. at the
University of Cambridge with Carl Rasmussen and Zoubin Ghahramani. Previous
to that, he worked on machine vision both with Kevin Murphy at the
University of British Columbia, and later at Google Research.  David also
co-founded Invenia, an energy forecasting and trading firm

 

 

 

Mitra Kelly

Academic Secretary

Princeton University

Computer Science Dept

35 Olden Street

Princeton NJ 08540

mkelly at cs.princeton.edu

609-258-4562

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/talks/attachments/20160217/307d8764/attachment.html>