scholarly journals Conservative Inference Rule for Uncertain Reasoning under Incompleteness

2009 ◽  
Vol 34 ◽  
pp. 757-821 ◽  
Author(s):  
M. Zaffalon ◽  
E. Miranda
Keyword(s):  
Expert Systems ◽  
Incomplete Information ◽  
Statistical Inference ◽  
Pattern Classification ◽  
Inference Rule ◽  
Bayesian Theory ◽  
Necessary Condition ◽  
Uncertain Reasoning ◽  
General Terms ◽  
Abstract Rule

In this paper we formulate the problem of inference under incomplete information in very general terms. This includes modelling the process responsible for the incompleteness, which we call the incompleteness process. We allow the process' behaviour to be partly unknown. Then we use Walley's theory of coherent lower previsions, a generalisation of the Bayesian theory to imprecision, to derive the rule to update beliefs under incompleteness that logically follows from our assumptions, and that we call conservative inference rule. This rule has some remarkable properties: it is an abstract rule to update beliefs that can be applied in any situation or domain; it gives us the opportunity to be neither too optimistic nor too pessimistic about the incompleteness process, which is a necessary condition to draw reliable while strong enough conclusions; and it is a coherent rule, in the sense that it cannot lead to inconsistencies. We give examples to show how the new rule can be applied in expert systems, in parametric statistical inference, and in pattern classification, and discuss more generally the view of incompleteness processes defended here as well as some of its consequences.

Toward Normative Expert Systems: Part I The Pathfinder Project

1992 ◽  
Vol 31 (02) ◽  
pp. 90-105 ◽  
Author(s):  
D. E. Heckerman ◽  
E. J. Horvitz ◽  
B. N. Nathwani
Keyword(s):  
Lymph Node ◽  
Expert System ◽  
Decision Theory ◽  
Expert Systems ◽  
Medical Knowledge ◽  
Uncertain Reasoning ◽  
Reasoning Under Uncertainty ◽  
Early Decision ◽  
Theoretical Results

Abstract:Pathfinder is an expert system that assists surgical pathologists with the diagnosis of lymph-node diseases. The program is one of a growing number of normative expert systems that use probability and decision theory to acquire, represent, manipulate, and explain uncertain medical knowledge. In this article, we describe Pathfinder and our research in uncertain-reasoning paradigms that was stimulated by the development of the program. We discuss limitations with early decision-theoretic methods for reasoning under uncertainty and our initial attempts to use non-decision-theoretic methods. Then, we describe experimental and theoretical results that directed us to return to reasoning methods based in probability and decision theory.

scholarly journals Analysıs of Stages of Development, Current State and Prospects of the Expert Systems

2020 ◽  
Vol 19 (1) ◽  
Author(s):  
Nazila A. Rahimova ◽  
Vugar H. Abdullayev
Keyword(s):  
Expert Systems ◽  
Knowledge Base ◽  
First Generation ◽  
Second Generation ◽  
Current Status ◽  
Stages Of Development ◽  
Knowledge Based ◽  
General Terms ◽  
Current State ◽  
The Moment

The objects of the study are stages of development and modern state. In general terms, expert systems are knowledge-based systems. This paper focuses on the components and principles of expert systems. Expert systems are also described. The components of expert systems include knowledge base, logical impact mechanism, user interface and decision-making. In addition, this article describes the capabilities of expert systems. One challenge is to identify the future prospects of expert systems. The research examined the expert system and its significance. It also focuses on generations of expert systems. The first generation of expert systems includes systems created before 1990. This article discusses SAINT, DENDRAL and HEARSAY-1. The features of this expert systems are also discussed here. First-generation expert systems are research prototypes. As a result, the foundations of artificial intelligence were developed. Mostly first-generation expert systems were used as a passive assistant expert. The second generation of expert systems refers to systems created since 1990. Features of second-generation expert systems include dynamism, interactivity, and processing of disparate knowledge. Unlike first-generation expert systems, these systems are able to test the completeness of the knowledge base, to process fuzzy knowledge. Their main difference is the ability to integrate second-generation expert systems with existing systems. At the moment, statistical and dynamic expert systems are distinguished. This article describes the current status of both types. Here are also discussed the tools of statistical and dynamic expert systems. At the end, possible prospects of expert systems are received.

Diabetes Mellitus - Evaluating the Diagnostic Probabilities

2011 ◽  
pp. 169-177
Author(s):  
Adi Armoni
Keyword(s):  
Diabetes Mellitus ◽  
Decision Making ◽  
Expert System ◽  
Expert Systems ◽  
Knowledge Base ◽  
Decision Maker ◽  
Knowledge Bases ◽  
Bayesian Theory ◽  
Logical Conclusion ◽  
Human Decision

The article examines the behavior of the human decision-maker. It surveys research in which about 90 physicians specializing in various fields and with different degrees of seniority participated. It tackles the question of whether it is possible to found the majority of the knowledge bases of the expert systems on the Bayesian theory. We will discuss the way of decision making conforming to the probabilities evaluated according to the Bayesian theory. The logical conclusion, therefore, is that the development of a knowledge base for an expert system founded on probabilities calculated in accordance with the Bayesian theory must be carried out in a controlled manner and depend on the parameters mentioned above.

The Infancy of Solar-Type Stars and its Relevance for the Origin of Life

1997 ◽  
Vol 161 ◽  
pp. 267-282 ◽  
Author(s):  
Thierry Montmerle
Keyword(s):  
Main Sequence ◽  
Solar Nebula ◽  
Circumstellar Disks ◽  
T Tauri Stars ◽  
Necessary Condition ◽  
Sequence Evolution ◽  
T Tauri ◽  
Solar Type ◽  
Optical Domain ◽  
The Origin Of Life

AbstractFor life to develop, planets are a necessary condition. Likewise, for planets to form, stars must be surrounded by circumstellar disks, at least some time during their pre-main sequence evolution. Much progress has been made recently in the study of young solar-like stars. In the optical domain, these stars are known as «T Tauri stars». A significant number show IR excess, and other phenomena indirectly suggesting the presence of circumstellar disks. The current wisdom is that there is an evolutionary sequence from protostars to T Tauri stars. This sequence is characterized by the initial presence of disks, with lifetimes ~ 1-10 Myr after the intial collapse of a dense envelope having given birth to a star. While they are present, about 30% of the disks have masses larger than the minimum solar nebula. Their disappearance may correspond to the growth of dust grains, followed by planetesimal and planet formation, but this is not yet demonstrated.

Sign in / Sign up

Export Citation Format

Share Document