Results 1  10
of
162,743
On Learning FiniteState Quantum Sources
, 2009
"... We examine the complexity of learning the distributions produced by finitestate quantum sources. We show how prior techniques for learning hidden Markov models can be adapted to the quantum generator model to find that the analogous state of affairs holds: informationtheoretically, a polynomial nu ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
We examine the complexity of learning the distributions produced by finitestate quantum sources. We show how prior techniques for learning hidden Markov models can be adapted to the quantum generator model to find that the analogous state of affairs holds: informationtheoretically, a polynomial
FINITESTATE CONTROL OF UNCERTAIN SYSTEMS
, 1978
"... tlhj ~~iiL~~~1s16~L 9 _ _ ‘•~!j ~ OS iiI iii t is OI. 1.0 I~~~ ~ 28 ~ 25 ..."
Deeper Inside Finitestate Markov chains
, 2006
"... Abstract. The effective application of Markov chains has been paid much attention, and it has raised a lot of theoretical and applied problems. In this paper, we would like to approach one of these problems which is finding the longrun behavior of extremely hugestate Markov chains according to the ..."
Abstract
 Add to MetaCart
to the direction of investigating the structure of Markov Graph to reduce complexity of computation. We focus on the way to access to the finitestate Markov chain theory via Graph theory. We suggested some basic knowledge about state classification and a small project of modelling the structure and the moving
On the Controller Synthesis for FiniteState Markov Decision Processes
"... Abstract. We study the problem of effective controller synthesis for finitestate Markov decision processes (MDPs) and the class of properties definable in the logic PCTL extended with longrun average propositions. We show that the existence of such a controller is decidable, and we give an algorit ..."
Abstract
 Add to MetaCart
Abstract. We study the problem of effective controller synthesis for finitestate Markov decision processes (MDPs) and the class of properties definable in the logic PCTL extended with longrun average propositions. We show that the existence of such a controller is decidable, and we give
Learning FiniteState Machines  Statistical and Algorithmic Aspects
, 2013
"... The present thesis addresses several machine learning problems on generative and predictive models on sequential data. All the models considered have in common that they can be defined in terms of finitestate machines. On one line of work we study algorithms for learning the probabilistic analog of ..."
Abstract
 Add to MetaCart
The present thesis addresses several machine learning problems on generative and predictive models on sequential data. All the models considered have in common that they can be defined in terms of finitestate machines. On one line of work we study algorithms for learning the probabilistic analog
Weighted FiniteState Methods for SpellChecking and Correction
, 2014
"... ulty of Arts at the University of Helsinki in auditorium XII (in lecture room ..."
Abstract
 Add to MetaCart
ulty of Arts at the University of Helsinki in auditorium XII (in lecture room
5 An Extension of Finitestate Markov Decision Process and an Application of Grammatical Inference
"... In this chapter, we introduce the notion of simple contextfree decision processes, which are an extension of episodic finitestate Markov decision processes (MDPs). Intuitively, a simple contextfree decision process can be thought of as an episodic finitestate MDP with a stack. In fact, many rein ..."
Abstract
 Add to MetaCart
In this chapter, we introduce the notion of simple contextfree decision processes, which are an extension of episodic finitestate Markov decision processes (MDPs). Intuitively, a simple contextfree decision process can be thought of as an episodic finitestate MDP with a stack. In fact, many
On the Joint Decoding of LDPC Codes and FiniteState Channels via Linear Programming
"... Abstract—In this paper, the linear programming (LP) decoder for binary linear codes, introduced by Feldman, et al. is extended to jointdecoding of binaryinput finitestate channels. In particular, we provide a rigorous definition of LP jointdecoding pseudocodewords (JDPCWs) that enables evaluat ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Abstract—In this paper, the linear programming (LP) decoder for binary linear codes, introduced by Feldman, et al. is extended to jointdecoding of binaryinput finitestate channels. In particular, we provide a rigorous definition of LP jointdecoding pseudocodewords (JDPCWs) that enables
Investigations on Search Methods for Speech Recognition using Weighted FiniteState Transducers
, 2014
"... The search problem in the statistical approach to speech recognition is to find the most likely word sequence for an observed speech signal using a combination of knowledge sources, i.e. the language model, the pronunciation model, and the acoustic models of phones. The resulting search space is eno ..."
Abstract
 Add to MetaCart
is enormous. Therefore, an efficient search strategy is required to compute the result with a feasible amount of time and memory. The structured statistical models as well as their combination, the search network, can be represented as weighted finitestate transducers. The combination of the individual
Results 1  10
of
162,743