Studienarbeit
Filtern
Erscheinungsjahr
- 2010 (17) (entfernen)
Dokumenttyp
- Studienarbeit (17) (entfernen)
Schlagworte
- Mustererkennung (2)
- Robotik (2)
- Augmented Reality (1)
- Automatisches Beweisverfahren (1)
- BPMN (1)
- Balancetheorie (1)
- CB2 (1)
- Cascada (1)
- Computational logic (1)
- Computergraphik (1)
- DTI (1)
- E-KRHyper (1)
- E-Learning (1)
- EPC (1)
- EPK (1)
- Eclipse <Programmierumgebung> (1)
- Einchip-Computer (1)
- Enterprise Architect (1)
- Formale Ontologie (1)
- GPU Programmierung (1)
- Geometryshader (1)
- Geschäftsprozess (1)
- Headtracking (1)
- Heuristiken (1)
- Hyperspace-Modell (1)
- Interpretierer (1)
- Klassifikationsframework (1)
- Klausellogik (1)
- Medizinische Visualisierung (1)
- Metamodel (1)
- Mikrocontroller AVR (1)
- Network (1)
- Netzwerk (1)
- Netzwerk Protokollen (1)
- Neuronales Netz (1)
- OCL <Programmiersprache> (1)
- OWL <Informatik> (1)
- Objekterkennung (1)
- Oracle Generation (1)
- Oraklegenerierung (1)
- Pfadplanung (1)
- Plug in (1)
- Programmierumgebung (1)
- Protocol (1)
- Prädikatenlogik (1)
- Qt/C++ (1)
- Referenzmetamodell (1)
- RoboCup (1)
- SPARQL (1)
- Semantic Web (1)
- Sesame (1)
- Softwareentwicklung (1)
- Softwaremodellierung (1)
- Softwaretest (1)
- Softwaretesting (1)
- Specification (1)
- Spezifikation (1)
- Tableau <Logik> (1)
- Test Generation (1)
- Testgenerierung (1)
- UML (1)
- UML Activity Diagrams (1)
- UML Aktivitätsdiagramm (1)
- Universitäre Lehrveranstaltung (1)
- VNUML (1)
- Virtuelle Welt (1)
- Virtueller Raum (1)
- Visualisierung (1)
- Webservice Sail (1)
- Wii (1)
- Wii-Kamera (1)
- Wireshark (1)
- andLinux (1)
- andLinux. (1)
- backpropagation (1)
- bias (1)
- business process (1)
- networks (1)
- neural (1)
- path planning (1)
- recurrent (1)
- reference meta model (1)
- robotics (1)
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.