Share Email Print
cover

Proceedings Paper

Principles of automated learning in a GIS using an unlimited set of object-oriented persistent neurons
Author(s): Francois Bouille
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

HBDS offers a class-based integrated platform which is a kernel for GIS, in which anything is modeled by using persistent abstract data types, possibly in a fuzzy context. One of the most interesting and efficient concepts is the neuron; in HBDS, a neuron is an object of a class of neurons, this one being included in the hyperclass `neuron,' and thus inheriting an algorithmic `behavior' which is automatically activated when one of its `launchers,' attributes or links, is invoked by an external agent; then the neuron may perform actions on other components. This neuron is able to take into account its preceding experiences owing to some algorithms included in the neural engine. The neural models are particularly easy to design and develop, and represent an up-to-date methodology very promising in GIS. They nevertheless require a special training and education for new geographers as well as for those still active.

Paper Details

Date Published: 17 August 1994
PDF: 8 pages
Proc. SPIE 2357, ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision, (17 August 1994); doi: 10.1117/12.182857
Show Author Affiliations
Francois Bouille, Univ. P.M. Curie (France)


Published in SPIE Proceedings Vol. 2357:
ISPRS Commission III Symposium: Spatial Information from Digital Photogrammetry and Computer Vision
Heinrich Ebner; Christian Heipke; Konrad Eder, Editor(s)

© SPIE. Terms of Use
Back to Top