Representational Power of Restricted Boltzmann Machines and Deep Belief Networks.
Saved in:
| Title: | Representational Power of Restricted Boltzmann Machines and Deep Belief Networks. |
|---|---|
| Authors: | Le Roux, Nicolas1 lerouxni@iro.umontreal.ca, Bengio, Yoshua1 bengioy@iro.umontreal.ca |
| Source: | Neural Computation. Jun2008, Vol. 20 Issue 6, p1631-1649. 19p. 1 Diagram, 1 Graph. |
| Subjects: | Artificial neural networks, Functional representation, Computer programming, Artificial intelligence, Algorithms |
| Abstract: | Deep belief networks (DBN) are generative neural network models with many layers of hidden explanatory factors, recently introduced by Hinton,Osindero, and Teh (2006) alongwith a greedy layer-wise unsupervised learning algorithm. The building block of a DBN is a probabilistic model called a restricted Boltzmann machine (RBM), used to represent one layer of the model. Restricted Boltzmann machines are interesting because inference is easy in them and because they have been successfully used as building blocks for training deeper models. We first prove that adding hidden units yields strictly improvedmodeling power,while a second theorem shows that RBMs are universal approximators of discrete distributions. We then study the question of whether DBNs with more layers are strictly more powerful in terms of representational power. This suggests a new and less greedy criterion for training RBMs within DBNs. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
