An Object-Oriented Framework for the Simulation of Neural Nets

Abstract

The field of software simulators for neural networks has been ex(cid:173) panding very rapidly in the last years but their importance is still being underestimated. They must provide increasing levels of as(cid:173) sistance for the design, simulation and analysis of neural networks. With our object-oriented framework (SESAME) we intend to show that very high degrees of transparency, manageability and flexibil(cid:173) ity for complex experiments can be obtained. SESAME's basic de(cid:173) sign philosophy is inspired by the natural way in which researchers explain their computational models. Experiments are performed with networks of building blocks, which can be extended very eas(cid:173) ily. Mechanisms have been integrated to facilitate the construction and analysis of very complex architectures. Among these mech(cid:173) anisms are t.he automatic configuration of building blocks for an experiment and multiple inheritance at run-time.

Cite

Text

Linden et al. "An Object-Oriented Framework for the Simulation of Neural Nets." Neural Information Processing Systems, 1992.

Markdown

[Linden et al. "An Object-Oriented Framework for the Simulation of Neural Nets." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/linden1992neurips-objectoriented/)

BibTeX

@inproceedings{linden1992neurips-objectoriented,
  title     = {{An Object-Oriented Framework for the Simulation of Neural Nets}},
  author    = {Linden, A. and Sudbrak, Th. and Tietz, Ch. and Weber, F.},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {797-804},
  url       = {https://mlanthology.org/neurips/1992/linden1992neurips-objectoriented/}
}