A Theory and Methodology of Inductive Learning
Machine LearningPublished 1 January 1983
Ryszard S. Michalski
Citations231
SJR quartileQ1
SJR score1.15
SNIP2.14
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
The presented theory views inductive learning as a heuristic search through a space of symbolic descriptions, generated by an application of various inference rules to the initial observational statements. The inference rules include generalization rules, which perform generalizing transformations on descriptions, and conventional truth-preserving deductive rules. The application of the inference rules to descriptions is constrained by problem background knowledge, and guided by criteria evaluating the “quality” of generated inductive assertions. Based on this theory, a general methodology for learning structural descriptions from examples, called Star, is described and illustrated by a problem from the area of conceptual data analysis.
Keywords
Computer Science
The Philosophical ReviewA History of Western Philosophy.
2,032 Citations1946G. Watts Cunningham, Bertrand Russell
Elsevier eBooksSymbolic Logic and Mechanical Theorem Proving
1,472 Citations1973
This book contains an introduction to symbolic logic and a thorough discussion of mechanical theorem proving its applications and how it can be applied to various areas such as question answering, problem solving, program analysis, and program synthesis.
Journal of the ACMA Transformation System for Developing Recursive Programs
1,316 Citations1977R. M. Burstall, John Darlington
A system of rules for transforming programs, with the programs in the form of recursion equations, are described, with an initially very simple, lucid, and hopefully correct program transformed into a more efficient one by altering the recursion structure.
Information and ControlA formal theory of inductive inference. Part I
1,149 Citations1964Ray J. Solomonoff
Artificial IntelligenceLearning and executing generalized robot plans
1,035 Citations1972Richard Fikes, Peter E. Hart +1 more
Some major new additions to the STRIPS robot problem-solving system are described, including a process for generalizing a plan produced by STriPS so that problem-specific constants appearing in the plan are replaced by problem-independent parameters.
DSpace@MIT (Massachusetts Institute of Technology)Learning Structural Descriptions From Examples
1,007 Citations1970Patrick Henry Winston
Artificial IntelligenceDendral and meta-dendral: Their applications dimension
465 Citations1978Bruce G. Buchanan, Edward A. Feigenbaum
The DENDRAL and Meta-DENDRAL programs assist chemists with data interpretation problems and some chemical results produced by the programs are mentioned.
IEEE Transactions on Pattern Analysis and Machine IntelligencePattern Recognition as Rule-Guided Inductive Inference
405 Citations1980Ryszard S. Michalski
The paper formulates the theoretical framework and a method for inferring general and optimal descriptions of object classes from examples of classification or partial descriptions and an experimental computer implementation of the method is briefly described and illustrated by an example.
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)Version spaces: an approach to concept learning.
341 Citations1979Tom M. Mitchell
The version space approach has been implemented as one component of the Meta-DENDRAL program for learning production rules in the domain of chemical spectroscopy and proofs are given for the correctness of the method for representing version spaces, and of the associated concept learning algorithm, for any countably infinite concept description language.
Defense Technical Information Center (DTIC)On The Epistemological Status of Semantic Networks.
162 Citations1978Brachman,Ronald J
ComputingThe GUHA method of automatic hypotheses determination
156 Citations1966Petr Hájek, Ivan M. Havel +1 more
The GUHA method (General Unary Hypotheses Automaton) can be considered as a substitution for an intuition in a certain phase of scientific research, say, as an “offering of hypotheses”.
Elsevier eBooksA RECENT ADVANCE IN DATA ANALYSIS: Clustering Objects into Classes Characterized by Conjunctive Concepts
126 Citations1981Ryszard S. Michalski, Robert E. Stepp +1 more
The paper explains the recently introduced method of conjunctive conceptual clustering in terms of dynamic clustering and shows by an example its advantages over methods of numerical taxonomy from the viewpoint of cluster interpretation.
Communications of the ACMAn interference matching technique for inducing abstractions
124 Citations1978Frederick Hayes‐Roth, John McDermott
Three tasks solved by a program that uses an interference-matching algorithm are presented and several problems concerning the description of the training examples and the adequacy of interference matching are discussed.
ACM SIGART BulletinInductive inference of VL decision rules
115 Citations1977James B. Larson, Ryszard S. Michalski
The paper gives a brief descriFtion of methodology for rule induction and of a computer program which permits a more general rule format than typically used, and facilitates a compact and easy to understand expression of descriptions of different degrees of generality.
IEEE Transactions on Systems Man and CyberneticsThe Inference of Regular LISP Programs from Examples
98 Citations1978Alan W. Biermann
A class of LISP programs that is analogous to the finite-state automata is defined, and an algorithm is given for constructing such programs from examples of their input-output behavior.
Studies in logic and the foundations of mathematicsThe Aim of Inductive Logic
89 Citations1966Rudolf Carnap
The chapter indicates a theory of logical probability providing rules for inductive thinking, and explains the nature and purpose of inductive logic by showing the way it can be used in determining rational decisions.
Elsevier eBooksA SURVEY OF RESULTS IN GRAMMATICAL INFERENCE
87 Citations1972Alan W. Biermann, Jerome A. Feldman
Elsevier eBooksvariable-valued logic and its applications to pattern recognition and machine learning
59 Citations1977Ryszard S. Michalski
This chapter discusses the applications of variable-valued logic to pattern recognition and machine learning and presents some results on the application of an extended form of multi-valued Logic called variable- valued logic topattern recognition and artificial intelligence.
Elsevier eBooksAUTOMATIC INDUCTION OF CLASSIFICATION RULES FOR A CHESS ENDGAME
48 Citations1982Alen David Shapiro, Timothy B. Niblett
Inductively derived decision rules which correctly classify all legal Black-to-move positions in the king and pawn versus king endgame are derived using a technique of ‘structured’ induction.
UNSWorks (University of New South Wales, Sydney, Australia)Learning concepts by performing experiments
24 Citations1981Claude Sammut
Marvin is a program which is capable of learning concepts from many different environments by using a flexible description language based on first order predicate logic with quantifiers which provides Marvin with the knowledge necessary to learn the more complex concepts.
Purdue e-Pubs (Purdue University)Syntactic Shape Recognition Using Attributed Grammars.
22 Citations1978Kyung-Han You, Kai Fu
The method is extended to recognize partially distorted shapes and shows the advantage of the syntactic approach using attributed grammars over other existing shape recognition methods.
George Mason UniversityAn Experiment on Inductive Learning in Chess End Games
20 Citations1977Ryszard S. Michalski, Pericles Negri
This report presents first results from an experiment on the application of an inductive learning program called AQVAL/1 developed at the University of Illinois, to chess end games.
Artificial IntelligenceA powerful and efficient structural pattern recognition system
15 Citations1977Brian Cohen
This paper describes a general structural pattern recognition system that introduces code —a description language for patterns based on boolean logic and set theory and gives internal machine representations for concepts and objects which directly influence the efficiency of the system.
International Joint Conference on Artificial IntelligenceAutomated hypothesis generation using extended inductive resolution
13 Citations1975Charles O. Morgan
The f-resolution technique is shown to embody a version of Ockham's raror as a pruning heuristic and some promising experimental results are presented.
Pattern RecognitionLearning criterion and inductive behaviour
9 Citations1978Daniel Coulon, Daniel Kayser
It is shown that there are at least two kinds of inductive behaviours: to copy as exactly as possible the behaviour of a probability process and to learn the laws of a deterministic process from a set of observations.
IEEE Transactions on ComputersMaryanski's Grammatical Inferencer
8 Citations1979Gaines
A recent paper in this TRANSACTIONS1 on an automatic inference procedure for probabilistic grammars contained major anomalies that would mislead others attempting to reproduce the results and undermine the apparent validity of what is in fact a sound technique.
Communications of the ACMThe description list of concepts
6 Citations1962Ranan B. Banerji
A one-to-one correspondence is established between the recursive definition of a concept and its description list structure, which is built up from elementary list structures by a recursive process.