9 search results - page 2 / 2 » Training restricted Boltzmann machines using approximations ... |
FOCI
2007
IEEE
13 years 11 months ago
2007
IEEE
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
JMLR
2010
13 years 7 days ago
2010
Contrastive Divergence (CD) is a popular method for estimating the parameters of Markov Random Fields (MRFs) by rapidly approximating an intractable term in the gradient of the lo...
ICML
2008
IEEE
14 years 6 months ago
2008
IEEE
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
ICML
2010
IEEE
13 years 6 months ago
2010
IEEE
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...