Learning Feature Hierarchies with Centered Deep Boltzmann Machines

Details Learning Feature Hierarchies with Centered Deep Boltzmann Machines Learning Feature Hierarchies with Centered Deep Boltzmann Machines

2012-03-16

arxiv.org/abs/1203.3783v1

Statistics

Machine Learning

Scientific paper

Deep Boltzmann machines are in principle powerful models for extracting the hierarchical structure of data. Unfortunately, attempts to train layers jointly (without greedy layer-wise pretraining) have been largely unsuccessful. We propose a modification of the learning algorithm that initially recenters the output of the activation functions to zero. This modification leads to a better conditioned Hessian and thus makes learning easier. We test the algorithm on real data and demonstrate that our suggestion, the centered deep Boltzmann machine, learns a hierarchy of increasingly abstract representations and a better generative model of data.

Affiliated with

Also associated with

No associations

Rating

Learning Feature Hierarchies with Centered Deep Boltzmann Machines does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning Feature Hierarchies with Centered Deep Boltzmann Machines, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning Feature Hierarchies with Centered Deep Boltzmann Machines will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-352457