3 search results - page 1 / 1 » What Cannot be Learned with Bethe Approximations |
CORR
2012
Springer
12 years 8 days ago
2012
Springer
We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its B...
ALT
2011
Springer
12 years 4 months ago
2011
Springer
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
NIPS
2004
13 years 6 months ago
2004
Alternative splicing (AS) is an important and frequent step in mammalian gene expression that allows a single gene to specify multiple products, and is crucial for the regulation ...