University of Cambridge > Talks.cam > Machine Learning @ CUED > Deep Neural Networks: A Nonparametric Bayesian Approach with Local Competition

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Deep Neural Networks: A Nonparametric Bayesian Approach with Local Competition

Download to your calendar using vCal

If you have a question about this talk, please contact Robert Peharz .

The aim of this work is to enable inference of deep networks that retain high accuracy for the least possible model complexity, with the latter deduced from the data during inference. To this end, we revisit deep networks that comprise competing linear units, as opposed to nonlinear units that do not entail any form of (local) competition. In this context, our main technical innovation consists in an inferential setup that leverages solid arguments from Bayesian nonparametrics. We infer both the needed set of connections or locally competing sets of units, as well as the required floating point precision for storing the network parameters. Specifically, we introduce auxiliary discrete latent variables representing which initial network components are actually needed for modeling the data at hand, and perform Bayesian inference over them by imposing appropriate stick-breaking priors. As we experimentally show using benchmark datasets, our approach yields networks with less computational footprint than the state-of-the-art, and with no compromises in predictive accuracy.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

In person in the Max Perutz Lecture Theatre (CB2 0QH) and via Zoom link https://mrc-lmb-cam-ac-uk.zoom.us/j/97937314535?pwd=SciQzQiuFkLGF3ERwcMiLLTEbryUxV.1 Homerton College, Mary Allan Building, Bouling 8 & 9, Hills Road, Cambridge, CB2 8PQ Engineering Department -LR4

Other talks

Cooperation for Nature Title to be confirmed Group Work Title to be confirmed Discussion II continued Haematology and Palliative Care
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity