FAUN 1.1 User Manual

Simon König (), Frank Köller () and Michael H. Breitner ()
Additional contact information
Simon König: Institut für Wirtschaftsinformatik, Universität Hannover, http://www.iwi.uni-hannover.de/mitarbeiter/sk.html
Frank Köller: Institut für Wirtschaftsinformatik, Universität Hannover, http://www.iwi.uni-hannover.de/mitarbeiter/fk.html

No 16, IWI Discussion Paper Series from Institut für Wirtschaftsinformatik, Universität Hannover

Abstract: Today's neurocomputation usually is based on complete software emulation and is therefore often called neurosimulation. Inputs, outputs, neurons, synapses and weights are implemented in software. The neurosimulator FAUN (Fast Approximation with Universal Neural networks) enables supervised learning with 3- and 4-layered perceptrons and also radial basis functions. A FAUN user has to provide patterns, i.e. input-output pairs explaining a mathematical relation. Then artificial neural networks (ANN) are trained to learn the relation with a black-box approach. A well trained ANN reasonably interpolates and extrapolates between the patterns (generalization). This discussion paper shows in detail how FAUN works and gives several examples of use.

Keywords: artificial intelligence; neural network; neurosimulator; neurosimulation; SQP-training method (search for similar items in EconPapers)
JEL-codes: C61 C63 (search for similar items in EconPapers)
Date: 2005-08-04

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:ifw:iwidps:iwidps16

Ordering information: This working paper can be ordered from

Access Statistics for this paper

More papers in IWI Discussion Paper Series from Institut für Wirtschaftsinformatik, Universität Hannover
Address: Königsworther Platz 1, D-30167 Hannover
Contact information at EDIRC.
Series data maintained by RePEc-Administrator ().