Min-max classifiers: Learnability, design and application

Yang, P; Maragos, P

dc.contributor.author	Yang, P	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T01:43:20Z
dc.date.available	2014-03-01T01:43:20Z
dc.date.issued	1995	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/24089
dc.subject	Boolean Function	en
dc.subject	Character Recognition	en
dc.subject	Feature Vector	en
dc.subject	Feed Forward Neural Network	en
dc.subject	Handwritten Character Recognition	en
dc.subject	Image Processing	en
dc.subject	lms algorithm	en
dc.subject	Machine Learning	en
dc.subject	Mathematical Morphology	en
dc.subject	Pattern Classification	en
dc.subject	Supervised Learning	en
dc.subject	Training Algorithm	en
dc.subject	Value Function	en
dc.subject	Error Rate	en
dc.subject	Neural Network	en
dc.subject	Probably Approximately Correct	en
dc.title	Min-max classifiers: Learnability, design and application	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/0031-3203(94)00161-E	en
heal.identifier.secondary	http://dx.doi.org/10.1016/0031-3203(94)00161-E	en
heal.publicationDate	1995	en
heal.abstract	This paper introduces the class of min-max classifiers. These are binary-valued functions that can be used as pattern classifiers of both real-valued and binary-valued feature vectors. They are also lattice-theoretic generalization of Boolean functions and are also related to feed-forward neural networks and morphological signal operators.We studied supervised learning of these classifiers under the Probably Approximately Correct (PAC) model proposed	en
heal.journalName	Pattern Recognition	en
dc.identifier.doi	10.1016/0031-3203(94)00161-E	en