Asja Fischer og Christian Igel vinder Best Paper Award – Københavns Universitet

Videresend til en ven Resize Print Bookmark and Share

Datalogisk Institut, DIKU > Nyheder > DIKU-nyheder 2016 > Asja Fischer og Christ...

26. oktober 2016

Asja Fischer og Christian Igel vinder Best Paper Award

Best Paper Award

Tidligere ph.d.-studerende Asja Fischer og DIKUs professor Christian Igel har vundet Pattern Recognition Journal Best Paper Award 2014. Prisen gives til den bedste forskningsartikel publiceret i tidsskriftet Pattern Recognition.

It's the paper Training restricted Boltzmann machines: An introduction that has earned them the award. 

Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. They have attracted much attention as building blocks of deep learning systems called deep belief networks, and variants and extensions of RBMs have found application in a wide range of pattern recognition tasks. The article introduces RBMs from the viewpoint of Markov random fields (undirected graphical models).

Citation

Training restricted Boltzmann machines: An introduction. Asja Fischer, Christian Igel. Pattern Recognition. Volume 47, Issue 1, Jan. 2014, Pages 25-39

Abstract

Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. They have attracted much attention as building blocks for the multi-layer learning systems called deep belief networks, and variants and extensions of RBMs have found application in a wide range of pattern recognition tasks. This tutorial introduces RBMs from the viewpoint of Markov random fields, starting with the required concepts of undirected graphical models. Different learning algorithms for RBMs, including contrastive divergence learning and parallel tempering, are discussed. As sampling from RBMs, and therefore also most of their learning algorithms, are based on Markov chain Monte Carlo (MCMC) methods, an introduction to Markov chains and MCMC techniques is provided. Experiments demonstrate relevant aspects of RBM training.