Chapter

Adaptive and Intelligent Systems

Volume 6943 of the series Lecture Notes in Computer Science pp 297-307

Border Pairs Method – Constructive MLP Learning Classification Algorithm

  • Bojan PlojAffiliated withCarnegie Mellon UniversitySchool centre Ptuj, Higher vocational college
  • , Milan ZormanAffiliated withCarnegie Mellon UniversityFaculty of Electrical Engineering and Computer Science, University of Maribor
  • , Peter KokolAffiliated withCarnegie Mellon UniversityFaculty of Electrical Engineering and Computer Science, University of MariborFaculty of Health Sciences, University of Maribor

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In this paper we present Border pairs method, a constructive learning algorithm for multilayer perceptron (MLP). During learning with this method a near-minimal network architecture is found. MLP learning is conducted separately by individual layers and neurons. The algorithm is tested in computer simulation with simple learning patterns (XOR and triangles image), with traditional learning patterns (Iris and MNIST) and with noisy learning patterns. During the learning we have less possibilities to get stuck in the local minima, generalization of learning is good. Learning with noisy, multi-dimensional and numerous learning patterns work well. The Border pairs method also supports incremental learning.

Keywords

artificial intelligence machine learning multilayer perceptron constructive neural network border pairs method (BPM)