Training Restricted Boltzmann Machines with auxiliary function approach | IEEE Conference Publication | IEEE Xplore

Training Restricted Boltzmann Machines with auxiliary function approach


Abstract:

Restricted Boltzmann Machines (RBMs) are neural network models for unsupervised learning, but have recently found a wide range of applications as feature extractors for s...Show More

Abstract:

Restricted Boltzmann Machines (RBMs) are neural network models for unsupervised learning, but have recently found a wide range of applications as feature extractors for supervised learning algorithms. They have also received a lot of attention recently after being proposed as building blocks for deep belief networks. The success of these models raises the issue of how best to train them. At present, the most popular training algorithm for RBMs is the Contrastive Divergence (CD) learning algorithm. The aim of this paper is to seek for a new optimization algorithm tailored for training RBMs in the hope of obtaining a faster algorithm than the CD algorithm. We propose deriving a new training algorithm for RBMs based on an auxiliary function approach. Through an experiment on parameter training of an RBM, we confirmed that the present algorithm converged faster and to a better solution than the CD algorithm.
Date of Conference: 21-24 September 2014
Date Added to IEEE Xplore: 20 November 2014
Electronic ISBN:978-1-4799-3694-6

ISSN Information:

Conference Location: Reims, France

References

References is not available for this document.