logo Idiap Research Institute        
 [BibTeX] [Marc21]
Modular Object-Oriented Neural Network Simulators and Topology Generalizations
Type of publication: Conference paper
Citation: Thimm-94.1
Booktitle: Proceedings of the International Conference on Artificial Neural Networks (ICANN 94)
Volume: 1
Year: 1994
Publisher: Springer-Verlag
Location: Sorrento, Italy
Address: London, UK
ISBN: 3-540-19887-3
Abstract: A growing number of neural networks are based on topologies that deviate from the standard fixed first order fully interlayer connected ones. Although there currently exist a variety of neural network simulators, few are flexible enough to facilitate substantial topology alterations. Some novel modular object-oriented neural network simulators promise modifications and extensions to be made with minimal effort. Two of these simulators are described and compared: OpenSimulator (version 3.1) and Sesame (version 4.5). An extension of these simulators to high-order and ontogenic neural networks is outlined.
Userfields: dates={26--29 May, 1994}, language={English}, ipdmembership={neuron learning}, ipdhtml={https://www.idiap.ch/nn-papers/simulator/sim.html},
Keywords: high order neural network, neural network connectivity, neural network simulator, neural network topology, object-oriented, ontogenic neural network, OpenSimulator, Sesame, Sigma-Pi neural network
Projects Idiap
Authors Thimm, Georg
Grau, R.
Fiesler, Emile
Editors Marinaro, Maria
Morasso, Pietro G.
Added by: [UNK]
Total mark: 0
  • 94-03.pdf