We propose a learning algorithm that reuses knowledge acquired in past learning sessions to improve its performance on a new learning task. The method concerns visual learning and uses genetic programming to represent hypotheses, each of them being a procedure that processes visual primitives derived from the training images. The process of recognition is generative, i.e., a procedure is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This basic method is extended with a knowledge reuse mechanism that allows learners to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare both methods on a task of handwritten character recognition, and conclude that knowledge reuse leads to significant improvement of classification accuracy and reduces the risk of overfitting.
@INPROCEEDINGS { jaskowski07ECMLPlanLearn,
AUTHOR = { Wojciech Ja\'skowski and Krzysztof Krawiec and Bartosz Wieloch },
TITLE = { Evolutionary Learning with Cross-Class Knowledge Reuse for Handwritten Character Recognition },
BOOKTITLE = { Proceedings of Planning to Learn Workshop (PlanLearn) 2007 },
YEAR = { 2007 },
PAGES = { 21-30 },
MONTH = { sep },
ABSTRACT = { We propose a learning algorithm that reuses knowledge acquired in past learning sessions to improve its performance on a new learning task. The method concerns visual learning and uses genetic programming to represent hypotheses, each of them being a procedure that processes visual primitives derived from the training images. The process of recognition is generative, i.e., a procedure is supposed to restore the shape of the processed object by drawing its reproduction on a separate canvas. This basic method is extended with a knowledge reuse mechanism that allows learners to import genetic material from hypotheses that evolved for the other decision classes (object classes). We compare both methods on a task of handwritten character recognition, and conclude that knowledge reuse leads to significant improvement of classification accuracy and reduces the risk of overfitting. },
FILE = { jaskowski07ECMLPlanLearn.pdf:jaskowski07ECMLPlanLearn.pdf:PDF },
URL = { http://www.cs.put.poznan.pl/wjaskowski/pub/papers/jaskowski07ECMLPlanLearn.pdf },
KEYWORDS = { evolutionary computation, character recognition, genetic programming, visual learning, knowledge reuse, runes },
}