### 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 language | English (US) |
---|---|

Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |

Publisher | Publ by Int Soc for Optical Engineering |

Pages | 50-58 |

Number of pages | 9 |

Volume | 1706 |

ISBN (Print) | 0819408719 |

State | Published - 1992 |

Event | Adaptive and Learning Systems - Orlando, FL, USA Duration: Apr 20 1992 → Apr 21 1992 |

### Other

Other | Adaptive and Learning Systems |
---|---|

City | Orlando, FL, USA |

Period | 4/20/92 → 4/21/92 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Electrical and Electronic Engineering
- Condensed Matter Physics

### Cite this

*Proceedings of SPIE - The International Society for Optical Engineering*(Vol. 1706, pp. 50-58). Publ by Int Soc for Optical Engineering.

}

*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.

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 -