The field of software simulators for neural networks has been expanding very rapidly in the last years but their importance is still being underestimated. They must provide increasing levels of assistance 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 flexibility for complex experiments can be obtained. SESAME's basic design 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 easily. Mechanisms have been integrated to facilitate the construction and analysis of very complex architectures. Among these mechanisms are the automatic configuration of building blocks for an experiment and multiple inheritance at run-time.
[1]
P. Treleaven,et al.
THE PYGMALION NEURAL NETWORK PROGRAMMING ENVIRONMENT
,
1990
.
[2]
Matthew A. Wilson,et al.
GENESIS: A System for Simulating Neural Networks
,
1988,
NIPS.
[3]
Niels Mache,et al.
Recent developments of the SNNS neural network simulator
,
1991
.
[4]
Nigel Goddard,et al.
Rochester Connectionist Simulator
,
1989
.
[5]
Jacob M. J. Murre,et al.
The MetaNet Network Environment for the Development of Modular Neural Networks
,
1990
.
[6]
A. Linden,et al.
Combining multiple neural network paradigms and applications using SESAME
,
1992,
[Proceedings 1992] IJCNN International Joint Conference on Neural Networks.