In computer science, the use of log probabilities means representing probabilities in logarithmic space, instead of the standard interval. This has… (More)

Semantic Scholar uses AI to extract papers important to this topic.

2015

2015

- Yuri Burda, Roger B. Grosse, Ruslan Salakhutdinov
- AISTATS
- 2015

Markov random fields (MRFs) are difficult to evaluate as generative models because computing the test log-probabilities requires… (More)

Is this relevant?

Highly Cited

2014

Highly Cited

2014

- Bob Carpenter, Daniel Lee, +7 authors Peter Li
- 2014

Stan is a probabilistic programming language for specifying statistical models. A Stan program imperatively defines a log… (More)

Is this relevant?

Highly Cited

2014

Highly Cited

2014

- Ciprian Chelba, Tomas Mikolov, +4 authors Tony Robinson
- INTERSPEECH
- 2014

We propose a new benchmark corpus to be used for measuring progress in statistical language modeling. With almost one billion… (More)

Is this relevant?

Highly Cited

2009

Highly Cited

2009

- Pi-Chuan Chang, Huihsin Tseng, Daniel Jurafsky, Christopher D. Manning
- SSST@HLT-NAACL
- 2009

The prevalence in Chinese of grammatical structures that translate into English in different word orders is an important cause of… (More)

Is this relevant?

Highly Cited

2009

Highly Cited

2009

- Ruslan Salakhutdinov, Geoffrey E. Hinton
- NIPS
- 2009

We introduce a two-layer undirected graphical model, called a “Replicated Softmax”, that can be used to model and automatically… (More)

Is this relevant?

2008

2008

- Iain Murray, Ruslan Salakhutdinov
- NIPS
- 2008

We present a simple new Monte Carlo algorithm for evaluating probabilities of observations in complex latent variable models… (More)

Is this relevant?

Highly Cited

2008

Highly Cited

2008

- Ruslan Salakhutdinov, Iain Murray
- ICML
- 2008

Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for… (More)

Is this relevant?

Review

2006

Review

2006

- David A. Smith, Jason Eisner
- ACL
- 2006

When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set… (More)

Is this relevant?

Highly Cited

2005

Highly Cited

2005

- Martin J. Wainwright, Tommi S. Jaakkola, Alan S. Willsky
- IEEE Transactions on Information Theory
- 2005

We develop and analyze methods for computing provably optimal maximum a posteriori probability (MAP) configurations for a… (More)

Is this relevant?

Highly Cited

1999

Highly Cited

1999

One of the central issues in the use of principal component analysis (PCA) for data modelling is that of choosing the appropriate… (More)

Is this relevant?