Border Pairs Method – Constructive MLP Learning Classification Algorithm

  • Bojan Ploj
  • Milan Zorman
  • Peter Kokol
Conference paper

DOI: 10.1007/978-3-642-23857-4_30

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6943)
Cite this paper as:
Ploj B., Zorman M., Kokol P. (2011) Border Pairs Method – Constructive MLP Learning Classification Algorithm. In: Bouchachia A. (eds) Adaptive and Intelligent Systems. Lecture Notes in Computer Science, vol 6943. Springer, Berlin, Heidelberg

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) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Bojan Ploj
    • 1
  • Milan Zorman
    • 2
  • Peter Kokol
    • 2
    • 3
  1. 1.School centre PtujHigher vocational collegePtujSlovenia
  2. 2.Faculty of Electrical Engineering and Computer ScienceUniversity of MariborMariborSlovenia
  3. 3.Faculty of Health SciencesUniversity of MariborMariborSlovenia

Personalised recommendations