Showing papers in "Artificial Intelligence in 1990"
TL;DR: In this article, it was shown that probabilistic inference using belief networks is NP-hard and that it seems unlikely that an exact algorithm can be developed to perform inference efficiently over all classes of belief networks and that research should be directed toward the design of efficient special-case, average-case and approximation algorithms.
2,200 citations
TL;DR: In this article, the authors explore principles governing the rational balance among an agent's beliefs, goals, actions, and intentions, and show how agents can avoid intending all the foreseen side-effects of what they actually intend.
2,151 citations
TL;DR: In this paper, a number of families of nonmonotonic consequence relations, defined in the style of Gentzen [13], are studied from both proof-theoretic and semantic points of view.
1,651 citations
1,556 citations
TL;DR: A variation of minimax lookahead search, and an analog to alpha-beta pruning that significantly improves the efficiency of the algorithm, and a new algorithm, called Real-Time-A∗, for interleaving planning and execution, which proves that the algorithm makes locally optimal decisions and is guaranteed to find a solution.
1,071 citations
TL;DR: The tensor product representation rests on a principled analysis of structure; it saturates gracefully as larger structures are represented; it permits recursive construction of complex representations from simpler ones; it extends naturally to continuous structures and continuous representational patterns.
1,012 citations
TL;DR: This paper presents a connectionist architecture which automatically develops compact distributed representations for variable-sized recursive data structures, as well as efficient accessing mechanisms for them.
970 citations
TL;DR: The ACT theory of skill acquisition and its PUPS successor provide production-system models of the acquisition of skills such as LISP programming, geometry theorm-proving, and solving of algebraic equations.
569 citations
TL;DR: It is suggested that a program which can demonstrate expertise in the area of medical consultation will have to use a judicious combination of categorical and probabilistic reasoning—the former to establish a sufficiently narrow context and the latter to make comparisons among hypotheses and eventually to recommend therapy.
484 citations
TL;DR: Three different ways of mapping part-whole hierarchies into connectionist networks are described, suggesting that neural networks have two quite different methods for performing inference.
375 citations
TL;DR: In pilot trials, the learning environment successfully taught novices to troubleshoot and to mentally simulate circuit behavior, and the implications of this work for the design of intelligent learning environments are explored.
TL;DR: A parallel distributed processing model is described that learns to comprehend single clause sentences that assigns thematic roles to sentence constituents, disambiguates ambiguous words, instantiates vague words, and elaborates implied roles.
TL;DR: This paper describes a successful approach to concept learning for heuristic classification that has been applied to the domain of clinical audiology and achieved a competence level equaling that of human experts and far surpassing that of other machine learning programs.
TL;DR: In this paper, the authors present an approach to repair in which plan failures are described in terms of causal explanations of why they occurred, which are used to access abstract repair strategies, which can then be used to make specific changes to the faulty plans.
TL;DR: Two insights that arise when one studies the question "why and how is it that the authors say the same thing differently to different people, or even to the same person in different circumstances" are discussed.
TL;DR: In a recent publication, "A Method of Managing Evidential Reasoning in a Hierarchical Hypothesis Space" [1], Gordon and Shortliffe (G-S) study the application of Dempster-Shafer theory to evidential reasoning in a tree-structured hierarchy of hypotheses.
PARC1
TL;DR: This approach can be generalized if the set of components can be partitioned such that each of the components of a partition fail with equal probability but are much more or less likely to fail than those of other partitions.
TL;DR: Using the probably approximately correct framework developed in [12], Baum and Haussler have shown that if a neural network can be trained to automatically construct its own internal representations, then it might be better to settle for the system that works best.
TL;DR: A coherent way of interpolating three-dimensional data obtained by stereo, for example, with a simplicial polyhedral surface based on the use of the constrained Delaunay triangulation is proposed.
TL;DR: The point of the work is to show how neural networks can exhibit compositionality and distal access, two properties that distinguish symbol processing from lower-level cognitive functions such as pattern recognition.
TL;DR: In this article, a theory for the interpretation of 3D textures with oriented elements is proposed for the reconstruction of textured planes, which builds on two previous theories: a statistical one due to Witkin, and Kanatani's "Buffon" transform.
TL;DR: A system called PROUST is described which performs intention-based diagnosis of errors in novice PASCAL programs and achieves high performance in finding bugs in nontrivial student programs.
TL;DR: It is proved that, given as input a set of tables representing basic probability assignments m 1, …, m n over a frame of discernment Θ, and a set A ⊆ Θ , the problem of computing the combined basic probability value (m 1 … ⊕ m n )(A) is # P -complete.
TL;DR: This paper introduces the concept of Place Vocabularies as a useful symbolic description of the possible interactions and shows how this representation can be computed from metric data and used as a basis for qualitative envisionments of mechanism behavior.
TL;DR: Formal bounds are established on the efficacy of using the Hough transform to preselect likely subspaces of the search space, showing that the problem remains exponential, but that in practical terms the size of the problem is significantly decreased.
TL;DR: In this article, the main contribution is a precise characterization of the inferences performed by non-monotonic truth maintenance systems (TMSs), using two standard non-Monotonic formalisms: logic programming with the stable set semantics and autoepistemic logic.
TL;DR: P predictive value maximization (PVM), a heuristic search procedure through the hypothesis space of conjunctions and disjunctions of variables and their cutoff values, is outlined, where the goal is to find the best combination of tests for making a diagnosis.
TL;DR: It is shown that the stochastic simulation can be viewed as a sampling from the Gibbs distribution, which is useful in making statements about convergence of the simulation and finding the most likely instantiation of the Bayesian network.
TL;DR: In this paper, the shape from shading (SFS) problem is formulated as a computer vision problem and solved using a cost minimization approach which allows for noise and incorporates a regularization term in the cost function.
TL;DR: A program, called PLR (for Piecewise Linear Reasoner), that formalizes an analysis strategy employed by experts, that takes parameterized ordinary differential equations as input and produces a qualitative description of the solutions for all initial values.