fnnlib: a flexible C++ library for recurrent neural network simulations

  • This thesis introduces fnnlib, a C++ library for recurrent neural network simulations that I developed between October 2009 and March 2010 at Osaka University's Graduate School of Engineering. After covering the theory behind recurrent neural networks, backpropagation through time, recurrent neural networks with parametric bias, continuous-time recurrent neural networks, and echo state networks, the design of the library is explained. All of the classes as well as their interrelationships are presented along with reasons as to why certain design decisions were made. Towards the end of the thesis, a small practical example is shown. Also, fnnlib is compared to other neural network libraries.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Dennis Faßbender
URN:urn:nbn:de:kola-4612
Referee:Ulrich Furbach
Advisor:Björn Pelzer
Document Type:Study Thesis
Language:English
Date of completion:2010/11/17
Date of publication:2010/11/17
Publishing institution:Universität Koblenz-Landau, Campus Koblenz, Universitätsbibliothek
Granting institution:Universität Koblenz, Fachbereich 4
Release Date:2010/11/17
Tag:Neuronales Netz
backpropagation; bias; networks; neural; recurrent
Number of pages:52
Institutes:Fachbereich 4 / Institut für Informatik
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):License LogoEs gilt das deutsche Urheberrecht: § 53 UrhG