Abstract
The deep Boltzmann machine is a powerful model that extracts the hierarchical structure of observed data. While inference is typically slow due to its undirected nature, we argue that the emerging feature hierarchy is still explicit enough to be traversed in a feed forward fashion. The claim is corroborated by training a set of deep neural networks on real data and measuring the evolution of the representation layer after layer. The analysis reveals that the deep Boltzmann machine produces a feed-forward hierarchy of increasingly invariant representations that clearly surpasses the layer-wise approach.
Original language | English |
---|---|
Pages (from-to) | 798-804 |
Number of pages | 7 |
Journal | Journal of Machine Learning Research |
Volume | 22 |
Publication status | Published - 2012 |
Externally published | Yes |
Event | 15th International Conference on Artificial Intelligence and Statistics, AISTATS 2012 - La Palma, Spain Duration: 2012 Apr 21 → 2012 Apr 23 |
ASJC Scopus subject areas
- Software
- Control and Systems Engineering
- Statistics and Probability
- Artificial Intelligence