Accession Number : ADA293109

Title :   PADO: Learning Tree Structured Algorithms for Orchestration into an Object Recognition System.

Descriptive Note : Research rept.,

Corporate Author : CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE

Personal Author(s) : Teller, Astro ; Veloso, Manuela

PDF Url : ADA293109

Report Date : 10 FEB 1995

Pagination or Media Count : 34

Abstract : Most artificial intelligence systems today work on simple problems and artificial domains because they rely on the accurate sensing of the task world. Object recognition is a crucial part of the sensing challenge and machine learning stands in a position to catapult object recognition into real world domains. Given that, to date, machine learning has not delivered general object recognition, we propose a different point of attack: the learning architectures themselves. We have developed a method for directly learning and combining algorithms in a new way that imposes little burden on or bias from the humans involved. This learning architecture, PADO, and the new results it brings to the problem of natural image object recognition is the focus of this report.

Descriptors :   *ALGORITHMS, *COMPUTER ARCHITECTURE, *COMPUTER VISION, *LEARNING, GLOBAL, DETECTION, HUMANS, ACCURACY, LEARNING MACHINES, TREES, IMAGES, RECOGNITION, ARTIFICIAL INTELLIGENCE, LIBRARIES, GRAY SCALE.

Subject Categories : Computer Programming and Software
      Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE