Skip to main content
Springer Nature Link
Log in

A survey of artificial neural network training tools

  • New applications of Artificial Neural Networks in Modeling & Control
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Artificial neural networks (ANN) are currently an additional tool which the engineer can use for a variety of purposes. Classification and regression are the most common tasks; however, control, modeling, prediction and forecasting are common tasks as well. For over three decades, the field of ANN has been the center of intense research. As a result, one of the outcomes has been the development of a large set of software tools used to train these kinds of networks, making the selection of an adequate tool difficult for a new user. This paper aims to help the ANN user choose the most appropriate tool for its application by providing a large survey of the solutions available, as well as listing and explaining their characteristics and terms of use. The paper limits itself to focusing on the tools which were developed for ANN and the relevant characteristics of these tools, such as the operating systems, hardware requirements, license types, architectures and algorithms available.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Huxhold WL, Henson TF, Bowman JD; IBM Corp., Houston, TX (1992) ANNIE: a simulated neural network for empirical studies and application prototyping. Annie. Simulation symposium. Proceedings of 25th annual USA, pp 2–8

  2. Aapo H (1999) Fast and robust fixed-point algorithms for independent component analysis. FastICA. IEEE Trans Neural Netw 10(3):626–663

    Article  Google Scholar 

  3. Yu H, Wilamowski BM (2009) Efficient and reliable training of neural networks. NNT—neural network trainer. IEEE human system interaction conference, Italy, May 21–23, pp 109–115

  4. Ian TN (2004) NETLAB: algorithms for pattern recognition. Springer, UK

    Google Scholar 

  5. Lopes N, Ribeiro B (2009) GPU implementation of the multiple back-propagation algorithms. In: Proceedings of intelligent data engineering and automated learning, Springer, pp 449–456

  6. Mark H, Eibe F, Geoffrey H, Bernhard P, Peter R, Ian HW (2009) The WEKA data mining software: an update, vol 11, no 1. SIGKDD Explorations

  7. Shankar A (2002) Annie—artificial neural network library. Last Update: 18th Jun 2002. Available at: http://annie.sourceforge.net/

  8. Leighton R (2010) Elegant software. Aspirin/migraines. Last accessed: 13rh Out 2010. Available at: http://www.elegant-software.com/software/aspirin/

  9. Tveter D (2010) The pattern recognition basis of AI neural networking software. Last accessed: 14th Out 2010. Available at: http://www.dontveter.com/nnsoft/nnsoft.html

  10. Neural Planner Software. EasyNN Plus. Last accessed: 12th Out 2010. Available at: http://www.easynn.com/

  11. Laboratory of Computer and Information Science. The FastICA package for MATLAB. Last accessed: 12th Out 2010. Available at: http://www.cis.hut.fi/projects/ica/fastica/

  12. GenAlgo Team. FuNeGen 1.0. Last accessed: 13th Out 2010. Available at: http://www.genalgo.com/index.php?option=com_content&task=view&id=211&Itemid=31

  13. Garrett A. MatLab central: fuzzy ART and fuzzy ARTMAP neural networks. Last accessed: 16th Out 2010. Available at: http://www.mathworks.com/matlabcentral/fileexchange/4306

  14. GENESIS. Last accessed: 15th Out 2010. Available at: http://www.genesis-sim.org/GENESIS/

  15. Aires de Sousa J. JATOON—Java tools for neural networks. Last accessed: 13rd Out 2010. Available at: http://www.dq.fct.unl.pt/staff/jas/jatoon/

  16. Zell A. JavaNNS—Java neural network simulator. Last accessed: 11rd Out 2010. Available at: http://www.ra.cs.unituebingen.de/software/JavaNNS/welcome_e.html

  17. Java Tips, Joone. Last accessed: 15th Out 2010. Available at: http://www.java-tips.org/javalibraries/neuralnetworks/joone.html

  18. Rohde D, Lens the light, efficient network simulator. Last accessed: 14th Out 2010. Available at: http://tedlab.mit.edu/~dr/Lens/

  19. Neural Decision Lab LLC, Software. LM_MLP, Nuclass and Numap. Last accessed: 13rd Out 2010. Available at: http://www.neuraldl.com/Software.php

  20. Lopes N. Multiple back-propagation. Last accessed: 16th Out 2010. Available at: http://mbp.sourceforge.net/

  21. Patrick Cloutier, Cristian Tibirna, Bernard Grandjean; Jules Thibault. NNFit (neural network fitting). Last accessed: 11rd Out 2010. Available at: http://www.gch.ulaval.ca/nnfit/english/index.html

  22. Ravn O, Nørgaard M. The NNSYSID toolbox for use with MatLab. Last accessed: 12nd Out 2010. Available at: http://www.iau.dtu.dk/research/control/nnsysid.html

  23. Wilamowski BM. Neural network training software for networks with arbitrarily connected neurons. Last accessed: 15th Out 2010. Available at: http://www.eng.auburn.edu/~wilambm/nnt/

  24. MathWorks. Neural network toolbox—design and simulate neural networks. Last accessed: 11th Out 2010. Available at: http://www.mathworks.com/products/neuralnet/

  25. Alyuda Research. ALYUDA. NeuroSolutions. Last accessed: 12nd Out 2010. Available at: http://www.alyuda.com/neural-networks-software.htm

  26. Softpedia. Neuroph is lightweight Java neural network framework. Last accessed: 15th Out 2010. Available at: http://neuroph.sourceforge.net/index.html

  27. NeuroDimension. NeuroSolutions–premier neural network development environment. Last accessed: 15th Out 2010. Available at: http://www.neurosolutions.com/

  28. Goodman P. Easy to use feed-forward backpropagation program. Nevada backpropagation (NevProp). Last accessed: 10th Out 2010. Available at: http://hpux.connect.org.uk/hppd/hpux/NeuralNets/NevProp-1.6/

  29. KTH. The NICO toolkit. Last update. Last accessed: 14th Out 2010. Available at: http://nico.nikkostrom.com/

  30. The PDP++ Software Home Page. Last accessed: 10th Out 2010. Available at: http://archive.cnbc.cmu.edu/Resources/PDP%2B%2B/PDP%2B%2B.html

  31. Runtime Software. Pythia—The neural network designer. Last accessed: 16th Out 2010. Available at: http://www.vyomlinks.com/download/pythia-the-neural-network-designerv1.00-2523.html

  32. Zell A. Stuttgart neural network simulator. Last accessed: 11rd Out 2010. Available at: http://www.nada.kth.se/~orre/snns-manual/

  33. Laboratory of Computer and Information Science. SOM Toolbox 2.0. Last accessed: 12th Out 2010. Available at: http://www.cis.hut.fi/projects/somtoolbox/

  34. Hynninen J. SOM_PAK and LVQ_PAK. Last accessed: 14th Out 2010. Available at: http://www.cis.hut.fi/research/som-research/nnrc-programs.shtml

  35. Statsoft. Statistica. Last accessed: 17th Out 2010. Available at: http://www.statsoft.com/

  36. Collobert R. Torch. Last accessed: 14th Out 2010. Available at: http://www.torch.ch/

  37. TrajanSoftware. TRAJAN 6.0 PROFESSIONAL. Last accessed: 9th Out 2010. Available at: http://www.trajan-software.demon.co.uk/

  38. Zhang QJ, Carleton University. NeuroModeler. Last accessed: 6th Jan 2012. Available at: http://neuroweb.doe.carleton.ca

  39. Heaton Research and Encog. Encog Java and DotNet neural network framework. Encog. Last accessed: 6th Jan 2012. Available at: http://www.heatonresearch.com/encog

  40. Vibert J-F, Alvarez F. XNBC: a software package to simulate biological neural networks for research and education. XNBC. Last accessed: 17th Out 2010. Available at: http://www.b3e.jussieu.fr/xnbc/

  41. Gewaltig M-O. Nest initiative. Nest. Last accessed: 17th Out 2010. Available at: http://www.nest-initiative.org

Download references

Acknowledgments

The authors would like to acknowledge the Portuguese Foundation for Science and Technology for their support in this work through the project PEst-OE/EEI/LA0009/2011.

Author information

Authors and Affiliations

  1. Madeira Interactive Technologies Institute and Competence Center of Exact Science and Engineering, University of Madeira, 9000-390, Funchal, Portugal

    Darío Baptista & Fernando Morgado-Dias

Authors
  1. Darío Baptista
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Fernando Morgado-Dias
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Darío Baptista.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Baptista, D., Morgado-Dias, F. A survey of artificial neural network training tools. Neural Comput & Applic 23, 609–615 (2013). https://doi.org/10.1007/s00521-013-1408-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-013-1408-9

Keywords