Genetic programming techniques for hand written digit recognition

A.D. Parkins

doi:10.1016/j.sigpro.2004.07.027

Genetic programming techniques for hand written digit recognition

2004-12-01

29

PRE

AI

DOI：10.1016/j.sigpro.2004.07.027

原文链接

原文求助

摘要

En 中文

Genetic programming is the implementation of the paradigm of the survival of the fittest from the natural world in the world of computation. Genetic programming is used to automatically create solutions to problems where the governing mechanisms are unknown. In this paper we apply genetic programming to the recognition of hand written digits from the USPS data set. To our knowledge there have been no results presented on this data set using genetic programming. We have introduced some variations on the selection and evolution methods normally used in genetic programming systems, in particular: aged members, directed crossover, inter-output crossover and node mutation. (C) 2004 Elsevier B.V. All rights reserved.

Keyword:

genetic programming

evolutionary

USPS

hand-written

digits

classifier

carrier nodes

Genetic programming techniques for hand written digit recognition

摘要

AI总结

期刊

机构

引用论文