publication . Article . 2003

"Accelerated Perceptron": A Self-Learning Linear Decision Algorithm

Zuev, Yu. A.;
Open Access English
  • Published: 01 Jan 2003
  • Publisher: Минск, БГУ
  • Country: Belarus
Abstract
The class of linear decision rules is studied. A new algorithm for weight correction, called an "accelerated perceptron", is proposed. In contrast to classical Rosenblatt's perceptron this algorithm modifies the weight vector at each step. The algorithm may be employed both in learning and in self-learning modes. The theoretical aspects of the behaviour of the algorithm are studied when the algorithm is used for the purpose of increasing the decision reliability by means of weighted voting. In this case the simple majority vote may be used as initial decision.
Subjects
free text keywords: :ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика [ЭБ БГУ]
Related Organizations
Download from
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue