Abstract | ||
---|---|---|
The spike-and-slab restricted Boltzmann machine (ssRBM) is defined to have both a real-valued “slab” variable and a binary “spike” variable associated with each unit in the hidden layer. The model uses its slab variables to model the conditional covariance of the observation-thought to be important in capturing the statistical properties of natural images. In this paper, we present the canonical s... |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TPAMI.2013.238 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | Field | DocType |
Slabs,Data models,Vectors,Feature extraction,Covariance matrices,Training,Standards | Restricted Boltzmann machine,Data modeling,Boltzmann machine,MNIST database,Pattern recognition,Computer science,Feature extraction,Unsupervised learning,Artificial intelligence,Probabilistic logic,Feature learning | Journal |
Volume | Issue | ISSN |
36 | 9 | 0162-8828 |
Citations | PageRank | References |
10 | 0.50 | 33 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aaron C. Courville | 1 | 6671 | 348.46 |
Guillaume Desjardins | 2 | 490 | 27.99 |
James Bergstra | 3 | 1784 | 166.50 |
Yoshua Bengio | 4 | 42677 | 3039.83 |