The perceptron with dynamic margin

DOI10.1007/978-3-642-24412-4_18MaRDI QIDQ3093951zbMATH OpenOpenAlexFDO

Authors C. Panagiotakopoulos, Petroula Tsampouka

Publication date 19 October 2011

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1105.6041

zbMATH Keywords

classificationmaximum marginonline learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Abstract: The classical perceptron rule provides a varying upper bound on the maximum margin, namely the length of the current weight vector divided by the total number of updates up to that time. Requiring that the perceptron updates its internal state whenever the normalized margin of a pattern is found not to exceed a certain fraction of this dynamic upper bound we construct a new approximate maximum margin classifier called the perceptron with dynamic margin (PDM). We demonstrate that PDM converges in a finite number of steps and derive an upper bound on them. We also compare experimentally PDM with other perceptron-like algorithms and support vector machines on hard margin tasks involving linear kernels which are equivalent to 2-norm soft margin.

Recommendations

• Learning Theory
• 10.1162/15324430260185600
• On-line learning through simple perceptron learning with a margin
• A kernel-based perceptron with dynamic memory
• A deterministic and polynomial modified perceptron algorithm

Cited in

(7)

• Enlarging the margins in perceptron decision trees
• A kernel-based perceptron with dynamic memory
• The maximum cosine framework for deriving perceptron based linear classifiers
• 10.1162/15324430260185600
• Noise tolerant variants of the perceptron algorithm
• Learning Theory
• Saturated perceptrons for maximum margin and minimum misclassification error

This page was built for publication: The perceptron with dynamic margin

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093951)