MLP - Multilayer Perceptron Training

Download

Note: The table package contains some auxiliary programs for preprocessing the data files.

Description

MLP is a set of programs to train a multilayer perceptron (an artificial neural network), to execute it to predict outcomes for new data, and to do a sensitivity analysis for a trained network on given data.

More details about these programs (included in the source package).

If you have trouble executing the programs on Microsoft Windows, check whether you have the Microsoft Visual C++ Redistributable for Visual Studio 2022 (see under "Other Tools and Frameworks") installed, as the programs were compiled with Microsoft Visual Studio 2022.

A graphical user interface to these command line programs (MLPGUI, written in Java) can be found here.

An introduction to neural networks and multilayer perceptrons in particular can be found in:

• Computational Intelligence - A Methodological Introduction
  Rudolf Kruse, Christian Borgelt, Frank Klawonn, Christian Moewes, Georg Ruß, Matthias Steinbrecher and Pascal Held
  Springer-Verlag, Berlin/Heidelberg, Germany 2013, ISBN 978-1-4471-5012-1
  (488 pages, in English)
• Computational Intelligence
  Rudolf Kruse, Christian Borgelt, Frank Klawonn, Christian Moewes, Georg Ruß, and Matthias Steinbrecher
  Vieweg+Teubner Verlag, Wiesbaden, Germany 2011, ISBN 978-3-8348-1275-9
  (461 pages, in German)
• Neuro-Fuzzy-Systeme - Von den Grundlagen Neuronaler Netze zu modernen Fuzzy-Systemen
  Detlef Nauck, Christian Borgelt, Frank Klawonn und Rudolf Kruse.
  Vieweg-Verlag, Wiesbaden, Germany 2003, ISBN 3-528-25265-0
  (448 pages, in German)