Inductive learning using generalized distance measures

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper briefly reviews the two currently dominant paradigms in machine learning - the connectionist network (CN) models and symbol processing (SP) systems; argues for the centrality of knowledge representation frameworks in learning; examines a range of representations in increasing order of complexity and measures of similarity or distance that are appropriate for each of them; introduces the notion of a generalized distance measure (GDM) and presents a class of GDM-based inductive learning algorithms (GDML). GDML are motivated by the need for an integration of symbol processing (SP) and connectionist network (CN) approaches to machine learning. GDM offer a natural generalization of the notion of distance or measure of mismatch used in a variety of pattern recognition techniques (e.g., k-nearest neighbor classifiers, neural networks using radial basis functions, and so on) to a range of structured representations such strings, trees, pyramids, association nets, conceptual graphs, etc. which include those used in computer vision and syntactic approaches to pattern recognition. GDML are a natural extension of generative or constructive learning algorithms for neural networks that enable an adaptive and parsimonious determination of the network topology as well as the desired weights as a function of learning Applications of GDML include tasks such as planning, concept learning, and 2- and 3-dimensional object recognition. GDML offer a basis for a natural integration of SP and CN approaches to the construction of intelligent systems that perceive, learn, and act.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherPubl by Int Soc for Optical Engineering
Pages50-58
Number of pages9
Volume1706
ISBN (Print)0819408719
StatePublished - 1992
EventAdaptive and Learning Systems - Orlando, FL, USA
Duration: Apr 20 1992Apr 21 1992

Other

OtherAdaptive and Learning Systems
CityOrlando, FL, USA
Period4/20/924/21/92

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Fingerprint Dive into the research topics of 'Inductive learning using generalized distance measures'. Together they form a unique fingerprint.

Cite this