Results 11  20
of
160
OPUS: An efficient admissible algorithm for unordered search
 Journal of Artificial Intelligence Research
, 1995
"... OPUS is a branch and bound search algorithm that enables efficient admissible search through spaces for which the order of search operator application is not significant. The algorithm’s search efficiency is demonstrated with respect to very large machine learning search spaces. The use of admissibl ..."
Abstract

Cited by 87 (14 self)
 Add to MetaCart
(Show Context)
OPUS is a branch and bound search algorithm that enables efficient admissible search through spaces for which the order of search operator application is not significant. The algorithm’s search efficiency is demonstrated with respect to very large machine learning search spaces. The use of admissible search is of potential value to the machine learning community as it means that the exact learning biases to be employed for complex learning tasks can be precisely specified and manipulated. OPUS also has potential for application in other areas of artificial intelligence, notably, truth maintenance. 1.
A Proof Procedure Using Connection Graphs
 JACM
, 1975
"... Various deficiencies of resolution systems are investigated and a new theoremproving system designed to remedy those deficiencms is presented The system is notable for eliminating redundancies present in SLresolutlon, for incorporating preprocessing procedures, for liberahzing the order in which ..."
Abstract

Cited by 83 (6 self)
 Add to MetaCart
(Show Context)
Various deficiencies of resolution systems are investigated and a new theoremproving system designed to remedy those deficiencms is presented The system is notable for eliminating redundancies present in SLresolutlon, for incorporating preprocessing procedures, for liberahzing the order in which subgoals can be activated, for incorporating multidirectmnal searches, and for giving immediate access to pairs of clauses which resolve Examples of how the new system copes with the deficiencies of other theoremproving systems are chosen from the areas of predicate logic programming and language parsing. The paper emphasizes the historical development of the new system, beginning as a supplement to SLresolution in the form of classification trees and incorporating an analogue of the Waltz algorithm for picture Interpretation The paper ends with a discussion of the opportunities for using lookahead to guide the search for proofs
Connectionist Probability Estimation in HMM Speech Recognition
 IEEE Transactions on Speech and Audio Processing
, 1992
"... This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system, This is achieved through a statistical understanding of connectionist networks as probability estimators, first elucidated by Herve Bourlard. We review the basis of HMM speech ..."
Abstract

Cited by 80 (23 self)
 Add to MetaCart
(Show Context)
This report is concerned with integrating connectionist networks into a hidden Markov model (HMM) speech recognition system, This is achieved through a statistical understanding of connectionist networks as probability estimators, first elucidated by Herve Bourlard. We review the basis of HMM speech recognition, and point out the possible benefits of incorporating connectionist networks. We discuss some issues necessary to the construction of a connectionist HMM recognition system, and describe the performance of such a system, including evaluations on the DARPA database, in collaboration with Mike Cohen and Horacio Franco of SRI International. In conclusion, we show that a connectionist component improves a state of the art HMM system. ii Part I INTRODUCTION Over the past few years, connectionist models have been widely proposed as a potentially powerful approach to speech recognition (e.g. Makino et al. (1983), Huang et al. (1988) and Waibel et al. (1989)). However, whilst connec...
The Computational Complexity of Cartographic Label Placement
, 1991
"... We examine the computational complexity of cartographic label placement, a problem derived from the cartographer's task of placing text labels adjacent to map features in such a way as to minimize overlaps with other labels and map features. Cartographic label placement is one of the most time ..."
Abstract

Cited by 71 (4 self)
 Add to MetaCart
We examine the computational complexity of cartographic label placement, a problem derived from the cartographer's task of placing text labels adjacent to map features in such a way as to minimize overlaps with other labels and map features. Cartographic label placement is one of the most timeconsuming tasks in the production of maps. Consequently, several attempts have been made to automate the labelplacement task for some or all classes of cartographic features (punctual, linear, or areal features), but all previously published algorithms for the most basic taskpointfeaturelabel placement either exhibit worstcase exponential time complexity, or incorporate incomplete heuristics that may fail to find an admissible labeling even when one exists. The computational complexity of label placement is therefore a matter of practical significance in automated cartography. We show that admissible label placement is NPcomplete, even for very simple versions of the problem. Thus, no ...
The effect of representation and knowledge on goaldirected exploration with reinforcement learning algorithms: The proofs
, 1995
"... Abstract. We analyze the complexity of online reinforcementlearning algorithms applied to goaldirected exploration tasks. Previous work had concluded that, even in deterministic state spaces, initially uninformed reinforcement learning was at least exponential for such problems, or that it was of ..."
Abstract

Cited by 60 (5 self)
 Add to MetaCart
(Show Context)
Abstract. We analyze the complexity of online reinforcementlearning algorithms applied to goaldirected exploration tasks. Previous work had concluded that, even in deterministic state spaces, initially uninformed reinforcement learning was at least exponential for such problems, or that it was of polynomial worstcase timecomplexity only if the learning methods were augmented. We prove that, to the contrary, the algorithms are tractable with only a simple change in the reward structure (“penalizing the agent for action executions”) or in the initialization of the values that they maintain. In particular, we provide tight complexity bounds for both Watkins ’ Qlearning and Heger’s Qhatlearning and show how their complexity depends on properties of the state spaces. We also demonstrate how one can decrease the complexity even further by either learning action models or utilizing prior knowledge of the topology of the state spaces. Our results provide guidance for empirical reinforcementlearning researchers on how to distinguish hard reinforcementlearning problems from easy ones and how to represent them in a way that allows them to be solved efficiently.
Simple and minimumcost satisfiability for goal models
, 2004
"... Abstract. Goal models have been used in Computer Science in order to represent software requirements, business objectives and design qualities. In previous work we have presented a formal framework for reasoning with goal models, in a qualitative or quantitative way, and we have introduced an algori ..."
Abstract

Cited by 59 (28 self)
 Add to MetaCart
Abstract. Goal models have been used in Computer Science in order to represent software requirements, business objectives and design qualities. In previous work we have presented a formal framework for reasoning with goal models, in a qualitative or quantitative way, and we have introduced an algorithm for forward propagating values through goal models. In this paper we focus on the qualitative framework and we propose a technique and an implemented tool for addressing two much more challenging problems: (1) find an initial assignment of labels to leaf goals which satisfies a desired final status of root goals by upward value propagation, while respecting some given constraints; and (2) find an minimum cost assignment of labels to leaf goals which satisfies root goals. The paper also presents preliminary experimental results on the performance of the tool using the goal graph generated by a case study involving the Public Transportation Service of Trentino (Italy). 1
Survey of the state of the art in human language technology
 Studies In Natural Language Processing, XIIXIII
, 1997
"... Sponsors: ..."
Formal Reasoning Techniques for Goal Models
 JOURNAL OF DATA SEMANTICS
, 2004
"... Over the past decade, goal models have been used in Computer Science in order to represent software requirements, business objectives and design qualities. Such models extend traditional AI planning techniques for representing goals by allowing for partially defined and possibly inconsistent goa ..."
Abstract

Cited by 53 (19 self)
 Add to MetaCart
Over the past decade, goal models have been used in Computer Science in order to represent software requirements, business objectives and design qualities. Such models extend traditional AI planning techniques for representing goals by allowing for partially defined and possibly inconsistent goals. This paper presents a formal framework for reasoning with such goal models. In particular, the paper proposes a qualitative and a numerical axiomatization for goal modeling primitives and introduces label propagation algorithms that are shown to be sound and complete with respect to their respective axiomatizations. In addition, the paper reports on experimental results on the propagation algorithms applied to a goal model for a US car manufacturer.
An efficient A* stack decoder algorithm for continuous speech recognition with a stochastic language model
 In Proc. IEEE ICASSP’93
, 1993
"... The stack decoder is an attractive algorithm for controlling the acoustic and language model matching in a continuous speech recognizer. A previous paper described a nearoptimal admissible Viterbi A * search algorithm for use with noncrossword acoustic models and nogrammar language models [16]. T ..."
Abstract

Cited by 51 (1 self)
 Add to MetaCart
(Show Context)
The stack decoder is an attractive algorithm for controlling the acoustic and language model matching in a continuous speech recognizer. A previous paper described a nearoptimal admissible Viterbi A * search algorithm for use with noncrossword acoustic models and nogrammar language models [16]. This paper extends this algorithm to include unigram language models and describes a modified version of the algorithm which includes the full (forward) decoder, crossword acoustic models and longerspan language models. The resultant algorithm is not admissible, but has been demonstrated to have a low probability of search error and to be very efficient.
Learning to Solve Markovian Decision Processes
, 1994
"... This dissertation is about building learning control architectures for agents embedded in finite, stationary, and Markovian environments. Such architectures give embedded agents the ability to improve autonomously the efficiency with which they can achieve goals. Machine learning researchers have d ..."
Abstract

Cited by 49 (3 self)
 Add to MetaCart
This dissertation is about building learning control architectures for agents embedded in finite, stationary, and Markovian environments. Such architectures give embedded agents the ability to improve autonomously the efficiency with which they can achieve goals. Machine learning researchers have developed reinforcement learning (RL) algorithms based on dynamic programming (DP) that use the agent's experience in its environment to improve its decision policy incrementally. This is achieved by adapting an evaluation function in such a way that the decision policy that is "greedy" with respect to it improves with experience. This dissertation focuses on finite, stationary and Markovian environments for two reasons: it allows the develop...