R.T. Ng and V.S. Subrahmanian. Empirical Probabilities in Monadic Deductive Databases. In Proc. Eighth Conf. Uncertainty in AI, pp. 215--222, Stanford, 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....[46] The propagation rules are backed up by a full proof procedure, xpoint theory, and a formal model theory which is shown to be probabilistic. This work is extended in [103] to cover the use of nonmonotonic negation, which makes it possible to capture some kind of default reasoning, and in [102] to cover objective probabilities. Now, it might not seem that objective probabilities raise any problems not covered by a scheme that can handle subjective probabilities, but this is not the case (due to a technical hitch with Herbrand universes) Despite this problem Ng and Subrahmanian provide ....

Ng, R. T. and Subrahmanian, V. S. (1992) Empirical probabilities in monadic deductive databases, Proceedings of the 8th Conference on Uncertainty in Articial Intelligence, Stanford, 215-222.

.... for the task, invent entirely new calculi, such as Dempster Shafer calculus [11,19,35] fuzzy logic [5,6,17,20,21,36,37] and (iii) those who remain within the traditional framework of probability theory, while attempting to equip the theory with computational facilities needed to perform AI tasks [1,10,13,27,28,29,30,32,33]. AI Communications ISSN 0921 7126, IOS Press. All rights reserved 2 We propose an approach to define the representation, inference, and control of uncertain information in the framework of DLP which is closely related to the second of the above categories. The main contributions of the paper ....

R.T. Ng and V.S. Subrahmanian. Empirical Probabilities in Monadic Deductive Databases. In Proc. Eighth Conf. Uncertainty in AI, pp. 215--222, Stanford, 1992.

....knowledge for a precise conclusion. 2 13 The numbers for T = are computed combinatorically, the numbers for T = T1 and T = T2 are taken from Fig. 5 and Fig. 7, respectively. 6 Related work The combination of taxonomic and uncertain knowledge was also examined by Ng and Subrahmanian [NS92a] von Rimscha [vR90] Heinsohn [Hei91] ffl Ng and Subrahmanian present an approach to integrate empirical probabilities in deductive databases. An empirical program consists of two parts, true false knowledge about classes of individuals (or single individuals) and empirical clauses ....

R. T. Ng and V. S. Subrahmanian. Empirical probabilities in monadic deductive databases. In Didier Dubois, Michael P. Wellman, Bruce D' Ambrosio, and Phillipe Smets, editors, Proc. of the 8 th Conference on Uncertainty in Artificial Intelligence, pages 215-- 222, Stanford, CA, Jul. 1992. Morgan Kaufmann Publishers.

....and O. Hence we can assume pos(B) for all B 2 B, since P (J(B) 0 entails J(B) and J(B) O. 3 In [LKKG94] we additionally consider correlation rules, comparative rules and conditional independencies. 4 P (J(B)jJ(A) is the conditional probability of J(B) under J(A) 5 The approach of [NS92a] is a representative of the statistical view. 3.3 Visualization of uncertain knowledge The Hasse diagrams of C T can be extended by labeled edges and marks to the nodes to represent also uncertain rules and positive probability statements. Since A x1 ;x2 Gamma Gamma Gamma Gamma Gamma B ( ....

R. T. Ng and V. S. Subrahmanian. Empirical probabilities in monadic deductive databases. In Didier Dubois, Michael P. Wellman, Bruce D' Ambrosio, and Phillipe Smets, editors, Proc. of the 8 th Conference on Uncertainty in Artificial Intelligence, pages 215--222, Stanford, CA, Jul. 1992. Morgan Kaufmann Publishers.

....information. The Prolog rules reason about the probability, at much more of a meta level than that proposed here. They can write down any independence assumptions and any conditional probability statements with the system giving no guidance as to what to write. In other work, Ng and Subrahmanian [36] have considered how to incorporate statistical probability [3] into logic programming. This should be seen as complementary to the work in this paper. 7 Conclusion This paper has presented a pragmatically motivated simple logic formulation that includes definite clauses and probabilities over ....

R. T. Ng and V. S. Subrahmanian. Empirical probabilities in monadic deductive databases. In Proc. Eighth Conf. on Uncertainty in Artificial Intelligence, pages 215--222, Stanford, Cal., July 1992.

....data models to capture it explicitly and appropriately. Being a topic of interest in AI for quite some period of time, it is picked up by database researchers recently. There is e.g. work in the relational context by Barbar a et al. BGMP92] and for deductive databases by Ng and Subramanian [NS92], Lakshmanan and Sadri [LS94] Our own previous work comprises a major project with the so called DUCK system for reasoning under a conditional probability model (see e.g. GKT91] TKG95] Before extending current OODBs towards uncertainty, the following aspects must be considered: Since ....

....sets of linear inequalities are solvable for all B 2 B: DT ;P [ f0 P C2I;T 6j=C= j=C B xCg (2) DT ;P [ f P C2I;T 6j=C= j=C B xC 1g (3) c) The complexity of the modeling consistency test is polynomial in the size of DT ;P . Proof: a) For similar considerations refer to [ADP91] [NS92] or [CL94] b) the claim directly follows from a) Let n = jfC 2 I j T 6j= C = gj. For i 2 [1 : k] let x i;0 2 [0; 1] n be solutions of the k systems of linear inequalities given by (2) For i 2 [1 : k] let x i;1 2 [0; 1] n be solutions of the k systems of linear inequalities given ....

[Article contains additional citation context not shown here]

R. T. Ng and V. S. Subrahmanian. Empirical probabilities in monadic deductive databases. In Didier Dubois, Michael P. Wellman, Bruce D' Ambrosio, and Phillipe Smets, editors, Proc. of the 8 th Conference on Uncertainty in Artificial Intelligence, pages 215--222, Stanford, CA, Jul. 1992. Morgan Kaufmann Publishers.

....of this structure is that essentially the context is a normal deductive database. In other words, our empirical deductive databases are downward compatible with existing deductive databases without probabilities. The framework presented here generalizes the preliminary framework reported in [20]. While the latter only supports unary predicates, the framework here provides for predicates of arbitrary arities. To deal with this generality and gain in expressive power, as we shall see later, we need to introduce a sophisticated notion of partitions and subpartitions, and to handle the ....

....Thus, the subjective probability of male(duke) is simultaneously 0 due to :male(duke) and between 0.65 and 0.7 due to the clause in E. Within our subjective framework, this discrepancy would render the program inconsistent. The framework presented here generalizes our framework reported in [20] which only supports unary predicate symbols. Thus, our language here allows us to express and reason with relationships among groups of elements in the domain of discourse. To deal with this generality and gain in expressive power, we need to adopt a more sophisticated notion of partitions, ....

R.T. Ng and V.S. Subrahmanian. (1992) Empirical Probabilities in Monadic Deductive Databases, Proc. 8th Conf. on Uncertainty in Artificial Intelligence, pp 215--222.

No context found.

R.T. Ng and V.S. Subrahmanian. Empirical Probabilities in Monadic Deductive Databases. In Proc. Eighth Conf. Uncertainty in AI, pp. 215--222, Stanford, 1992.

No context found.

R.T. Ng and V.S. Subrahmanian. Empirical Probabilities in Monadic Deductive Databases. In Proc. Eighth Conf. Uncertainty in AI, pp. 215--222, Stanford, 1992.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC