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

Fingerprint

learning
Learning algorithms
Pattern recognition
Learning systems
Processing
Neural networks
machine learning
Object recognition
Knowledge representation
Intelligent systems
Syntactics
pattern recognition
Computer vision
Classifiers
knowledge representation
Topology
Planning
computer vision
classifiers
pyramids

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Honavar, V. (1992). Inductive learning using generalized distance measures. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 1706, pp. 50-58). Publ by Int Soc for Optical Engineering.
Honavar, Vasant. / Inductive learning using generalized distance measures. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1706 Publ by Int Soc for Optical Engineering, 1992. pp. 50-58
@inproceedings{8390fd59c7d647ed8c688220f0aa23c4,
title = "Inductive learning using generalized distance measures",
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.",
author = "Vasant Honavar",
year = "1992",
language = "English (US)",
isbn = "0819408719",
volume = "1706",
pages = "50--58",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Publ by Int Soc for Optical Engineering",

}

Honavar, V 1992, Inductive learning using generalized distance measures. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 1706, Publ by Int Soc for Optical Engineering, pp. 50-58, Adaptive and Learning Systems, Orlando, FL, USA, 4/20/92.

Inductive learning using generalized distance measures. / Honavar, Vasant.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1706 Publ by Int Soc for Optical Engineering, 1992. p. 50-58.

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

TY - GEN

T1 - Inductive learning using generalized distance measures

AU - Honavar, Vasant

PY - 1992

Y1 - 1992

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0026969812&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026969812&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026969812

SN - 0819408719

VL - 1706

SP - 50

EP - 58

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Publ by Int Soc for Optical Engineering

ER -

Honavar V. Inductive learning using generalized distance measures. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1706. Publ by Int Soc for Optical Engineering. 1992. p. 50-58