We present a generalization of the query-by-committee active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically and empirically, with and without noise.

The algorithm is derived from the variational objective in the filtering setting and consists of an optimization procedure at each time step.

The purpose of this work is to study the general properties of this quantity and to show how they can be leveraged in practice.

Neural Information Processing Systems http://nips.cc/

In most applications, the output labels of learning problems have some structure that is crucial to consider. This includes natural language processing applications, where the output may be a sentence, a sequence of parts-of-speech tags, a parse tree, or a dependency graph.

In most applications, the output labels of learning problems have some structure that is crucial to consider. This includes natural language processing applications, where the output may be a sentence, a sequence of parts-of-speech tags, a parse tree, or a dependency graph.

This paper considers a number of related inverse filtering problems for hidden Markov models (HMMs).

Data serves as the fundamental basis for advancing deep learning.