Evolutionary computation framework for learning from visual examples

• Autorzy: Krawiec K.
• Konferencja: International Conference on Computer Analysis of Images and Patterns (9 ; 2001 ; Warszawa)
• Języki publikacji: EN

Abstrakty

EN

This paper investigates the use of evolutionary programming for the search of hypothesis space in visual learning tasks. The general goal of the project is to elaborate human-competitive procedures for pattern discrimination by means of learning based on the training data (set of images). In particular, the topic addressed here is the comparison between the "standard" genetic programming (as defined by Koza [13] and the genetic programming extended by local optimization of solutions, so-called genetic local search. The hypothesis formulated in the paper is that genetic local search provides better solutions (i.e. classifiers with higher predictive accuracy) than the genetic search without that extension. This supposition was positively verified in an extensive comparative experiment of visual learning concerning the recognition of handwritten characters.

Słowa kluczowe

EN

genetic local search; genetic programming; learning from examples; visual learning

PL

programowanie genetyczne; uczenie się wizualne

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2001
• Tom: Vol. 7, no 3-4
• Strony: 85--96
• Opis fizyczny: Bibliogr. 31 poz.,Rys., tab.,

Twórcy

autor

Krawiec K.

• Institute of Computing Science, Poznań University of Technology, Piotrowo 3A, 60965 Poznań, Poland,