Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
References
All Topics
Computer Science
Theoretical Computer Science

Semantic analysis of inductive reasoning

Profile image of Ewa OrlowskaEwa Orlowska

1986, Theoretical Computer Science

https://doi.org/10.1016/0304-3975(86)90167-2
visibility

…

description

9 pages

link

1 file

Abstract

Inductive learning is analysed from the semantic point of view. Processes of forming generalisations of concepts determined by examples of expert decisions are discussed. It is claimed that since concepts are relative to background knowledge, their inductive generalisations can be determined only approximately. Induction t-files are defined providing a method of forming generalisations preserving positive and/or negative instances of concepts.

Related papers

Guest editors introduction: Special issue on Inductive Logic Programming (ILP 2012)
Prasad Tadepalli

Machine Learning, 2014

View PDFchevron_right
A unifying view of knowledge representation for inductive learning
Christophe Giraud-Carrier

2000

Abstract This paper provides a foundation for inductive learning based on the use of higherorder logic for knowledge representation.

View PDFchevron_right
Inductive Logic
Branden Fitelson
View PDFchevron_right
Induction and decision procedures
Mahadevan Subramaniam

Revista de la Real Academia de Ciencias Exactas, …, 2004

Mechanization of inductive reasoning is an exciting research area in artificial intelligence and automated reasoning with many challenges. An overview of our work on mechanizing inductive reasoning based on the cover set method for generating induction schemes from terminating recursive function definitions and using decision procedures is presented. This paper particularly focuses on the recent work on integrating induction into decision procedures without compromising their automation. Resumen. Dentro del campo de la inteligencia artificial y del razonamiento automático, la mecanización del razonamiento inductivo es un área de investigación apasionante que se enfrenta a muchos retos. Se presenta una visión global del trabajo de los autores sobre la mecanización del razonamiento inductivo basado en el método de recubrimiento de conjuntos para la generación de esquemas de inducción a partir de definiciones de funciones recursivas con terminación que usa procedimientos de decisión. Este artículo se centra sobre todo en el trabajo reciente que se ha realizado con respecto a la integración de la inducción en los procedimientos de decisión sin comprometer su automatización.

View PDFchevron_right
On Integrating Inductive Learning with Prior Knowledge and Reasoning
Christophe Giraud-Carrier

1994

ABSTRACT Learning and reasoning are both aspects of what is considered to be intelligence. Their studies within AI have been separated historically, learning being the topic of neural networks and machine learning, and reasoning falling under classical (or symbolic) AI. However, learning and reasoning share many interdependencies, and the integration of the two may lead to more powerful models.

View PDFchevron_right
The origins of inductive logic programming: A prehistoric tale
Claude Sammut

Proceedings of the 3rd International Workshop on …, 1993

This paper traces the development of the main ideas that have led to the present state of knowledge in Inductive Logic Programming. The story begins with research in psychology on the subject of human concept learning. Results from this research influenced early efforts in Artificial Intelligence which combined with the formal methods of inductive inference to evolve into the present discipline of Inductive Logic Programming.

View PDFchevron_right
Logics for Qualitative Inductive Generalization
Diderik Batens

Studia Logica - An International Journal for Symbolic Logic, 2011

The paper contains a survey of (mainly unpublished) adaptive logics of inductive generalization. These defeasible logics are precise formula- tions of certain methods. Some attention is also paid to ways of handling background knowledge, introducing mere conjectures, and the research guiding capabilities of the logics.

View PDFchevron_right
A note on the evaluation of inductive concept classification procedures
Floriana Esposito, Claudia d'Amato

2008

Abstract. The limitations of deductive logic-based approaches at deriving operational knowledge from ontologies may be overcome by inductive (instancebased) methods, which are usually efficient and noise-tolerant. However the evaluation of such methods is made particularly difficult by the open-world semantics which may often cause individuals not to be deductively classified by the reasoner.

View PDFchevron_right
Interactive use of inductive approach for analyzing and developing conceptual structures
Ilze Birzniece

Proceedings - International Conference on Research Challenges in Information Science, 2012

Inductive learning algorithms learns classification from training examples and uses induced classifier for dealing with new instances. The use of conceptual data structures for classifier's input is making this task more complicated and classifier may meet the difficulties in class prediction. To broaden applicability of inductive learning based classifiers a collaborative approach between the system and human expert would be useful. The proposed interactive system in uncertain conditions can ask for human advice and improve its knowledge base with the rule derived from this interaction. Interactive inductive learning based classification system is proposed for helping to compare university study courses semi-automatically.

View PDFchevron_right
A proposal of categorisation for analysing inductive reasoning
María C Cañadas

PNA. Revista de Investigación en Didáctica de la Matemática

We present an analysis of the inductive reasoning of twelve Spanish secondary students in a mathematical problem-solving context. Students were interviewed while they worked on two different problems. Based on Polya´s steps and Reid’s stages for a process of inductive reasoning, we propose a more precise categorization for analyzing this kind of reasoning in our particular context. In this paper we present some results of a wider investigation (Cañadas, 2002). Una propuesta de categorización para analizar el razonamiento inductivo Presentamos un análisis del razonamiento inductivo de doce estudiantes de educación secundaria en un contexto de resolución de problemas matemáticos. Los estudiantes fueron entrevistados mientras trabajaban en dos problemas diferentes. Basándonos en los pasos considerados por Pólya y Reid para un proceso de razonamiento inductivo, proponemos una categorización más precisa para analizar este tipo de razonamiento en nuestro contexto particular. En este docum...

View PDFchevron_right

References (31)

  1. K. Ajdukiewicz, Logika Pragmatyezna (Pragmatic Logic) (PWN, Warsaw, 1965).
  2. R. Carnap, The aim of inductive logic, in: E. Nagel, P. Suppes and A. Tarski, eds., Logic, Methodology and Philosophy of Science (Stanford University Press, Stanford, 1962) 303-318.
  3. R. Carnap, The Continuum of Inductive Methods (The University of Chicago Press, Chicago, 1952).
  4. E.F. Codd, A relational model for large shared data banks, Comm. ACM 13 (1970) 377-387.
  5. P. Hajek and T. Havranek, Mechanizing Hypothesis Formation: Mathematical Foundations for a General Theory (Springer, Berlin, 1978).
  6. F. Hayes-Roth, Patterns of induction and associated knowledge acquisition algorithms, in" C. Chen, ed, Pattern Recognition and Artificial Intelligence (Academic Press, New York, 1976).
  7. F. Hayes-Roth and J. McDermott, An interference matching technique for inducing abstractions, Comm. ACM 21 (1978) 401-410.
  8. G.G. Hempel, Philosophy of Natural Science (Prentice-Hall, Englewood Cliffs, NJ, 1966).
  9. J. Hintikka, and P. Suppes, eds., Aspects of Inductive Logic (North-Holland, Amsterdam, 1966).
  10. E.B. Hunt, J. Matin and P. Stone, Experiments in Induction (Academic Press, New York, 1966).
  11. H. Kyburg, The Logical Foundations of Statistical Inference, Reidel Synthese Library 65 (Reidel, Dordrecht, 1974).
  12. I. Lakatos, ed., The Problem of Inductive Logic (North-Holland, Amsterdam, 1968).
  13. B. Me•tzer•Thesemantics•finducti•nandthep•ssibi•ity•fcomp•etesystems•finductiveinference• Artificial Intelligence 1 (1970) 189-192.
  14. R. Michalski, J.G. Carbonell and T.M. Mitchell, eds., Machine Learning, an Artificial Intelligence Approach (Tioga Publ., Palo Alto, CA, 1983).
  15. E. Minicozzi, Some natural properties of strong identification in inductive inference, Theoret. Comput. Sci. 2 (1976) 345-360.
  16. T.M. Mitchell, Generalization as search, Artificial Intelligence 18 (1982) 203-226.
  17. C.G. Morgan, Automated hypothesis generation using extended inductive resolution, Proc. 4th Internat. Joint Conf. on Artificial Intelligence, Tbilisi, U.S.S.R. (1975) 351-356.
  18. E. Orlowska, Representation of vague information, ICS PAS Rept. 503, Warsaw, 1963.
  19. E. Ortowska, Logic of nondeterministic information, Studia Logica (1984) to appear.
  20. E. Orlowska and Z. Pawlak, Logical foundations of knowledge representation, ICS PAS Rept. 537, Warsaw, 1984.
  21. Z. Pawlak, Information systems--theoretical foundations, Information Syst. 6 (1981) 205-218.
  22. Z. Pawlak, Rough sets, CompuL Inform. Sci. 11 (1982) 341-356.
  23. G.D. Plotkin, A note on inductive generalization, in: B. Meitzer and D. Michie, eds., Machine Intelligence 5 (American Elsevier, New York, 1970).
  24. G. Polya, Mathematics and Plausible Reasoning (Princeton University Press, Princeton, 1954).
  25. ICI~ Popper, The Logic of Scientific Discovery (Basic Books, New York, 1959).
  26. J.R. Quinlan, Discovering rules from large collections of examples: A case study, in: D. Michie, ed., Expert Systems in the Micro Electronic Age (Edinburgh University Press, Edinburgh, 1979).
  27. S.A. Vere, Induction of concepts in the predicate calculus, Proc. 4th lnternat. Joint Conf. on Artificial Intelligence, Tbilisi, U.S.S.R. (1975) 281-287.
  28. S.A. Vere, Inductive learning of relational productions, in: D. Waterman and F. Hayes-Roth, eds., Pattern Directed Inference Systems (Academic Press, New York, 1978).
  29. G. Von Wright, A Treatise on Induction and Probability (New York, 1951).
  30. P.H. Winston, Learning structural descriptions from examples, in: P.H. Winston, ed., The Psychology of Computer Vision (McGraw-Hill, New York, 1975).
  31. W. Zakowski, Approximations in the space (U, lr), Demonstratio Math. 16 (1983) 761-769.

Related papers

The basic inductive schema, inductive truisms, and the research-guiding capacities of the logic of inductive generalization
Diderik Batens

Logique Et Analyse, 2004

The aim of this paper is threefold. First, the sometimes slightly messy application of the conditional rule RC of the logic of inductive generalization is clarified by reducing this rule to a so-called basic schema BS. Next, some common truisms about inductive generalization are shown to be mistaken, but are also shown to be valid in special cases. Finally, and most importantly, it is shown that applications of the adaptive logic of inductive generalization to sets of data, possibly in the presence of background knowledge, invokes certain empirical tests and certain theoretically justified defeasible conjectures, which in a sensible way increase one's empirical and theoretical knowledge about a given domain.

View PDFchevron_right
The accuracy of concepts learned from induction
Gary Koehler

Decision Support Systems, 1993

Inductive learning methods identify a concept from a training sample consisting of positive and negative examples of a target concept. Several studies have shown how such methods could be used to determine rules for expert systems. The question addressed in this paper is: how accurate is the induced concept when used to classify the original domain or another close domain? We derive results that can be used to determine the accuracy of an induced concept. Two previously published applications of inductive learning are used to illustrate our results.

View PDFchevron_right
Towards a logical model of induction from examples and communication
Santiago Ontanon

2010

This paper focuses on a logical model of induction, and specifically of the common machine learning task of inductive concept learning (ICL). We define an "inductive derivation" relation, which characterizes which hypothesis can be induced from sets of examples, and show its properties. Moreover, we will also consider the problem of communicating inductive inferences between two agents, which corresponds to the multi-agent ICL problem. Thanks to the introduced logical model of induction, we will show that this communication can be modeled using computational argumentation.

View PDFchevron_right
Inductive reasoning: From Carnap to cognitive science
Peter Gärdenfors

The dominating models of inductive processes have been based on symbolic representations of knowledge. This was the explicit assumption of the Vienna school and most of Carnap's work on induction follows this principle. However, it is becoming increasingly clear that most cognitive phenomena in humans and animals are based on non-symbolic representations. As an alternative to symbolic representations of information and knowledge, this paper investigates a theory of "conceptual spaces." Such spaces consist of a number of "quality dimensions" which often are derived from perceptual mechanisms. They can be used to describe cognitive processes like concept formation and induction. A 'geometric' model of concept formation is proposed and its relation to prototype theory is discussed. It is shown that Carnap in his later writings was moving towards this approach to induction. It is also be argued that conceptual spaces are suitable for representing the results of information processing in connectionist systems.

View PDFchevron_right
A defeasible reasoning model of inductive concept learning from examples and communication
Santiago Ontanon

Artificial Intelligence, 2012

This paper introduces a logical model of inductive generalization, and specifically of the machine learning task of inductive concept learning (ICL). We argue that some inductive processes, like ICL, can be seen as a form of defeasible reasoning. We define a consequence relation characterizing which hypotheses can be induced from given sets of examples, and study its properties, showing they correspond to a rather well-behaved non-monotonic logic. We will also show that with the addition of a preference relation on inductive theories we can characterize the inductive bias of ICL algorithms. The second part of the paper shows how this logical characterization of inductive generalization can be integrated with another form of non-monotonic reasoning (argumentation), to define a model of multiagent ICL. This integration allows two or more agents to learn, in a consistent way, both from induction and from arguments used in the communication between them. We show that the inductive theories achieved by multiagent induction plus argumentation are sound, i.e. they are precisely the same as the inductive theories built by a single agent with all data.

View PDFchevron_right

Related topics

  • Theoretical Computer Science
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved