The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We ...
Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the...
Kristina Toutanova, Christopher D. Manning, Andrew...
In many reinforcement learning applications, the set of possible actions can be partitioned by the programmer into subsets of similar actions. This paper presents a technique for ...
We present a technique that enables the use of finite model finding to check the satisfiability of certain formulas whose intended models are infinite. Such formulas arise when us...
Window Abstraction for Infinite Markov Chains Thomas A. Henzinger1 , Maria Mateescu1 , and Verena Wolf1,2 1 EPFL, Switzerland 2 Saarland University, Germany Abstract. We present an...