The MetaNet Network Environment for the Development of Modular Neural Networks
暂无分享,去创建一个
The MetaNet network environment allows users to build and examine modular neural networks, and to specify and run complex simulations. It consists of a graphical editor, a network compiler and a graphical (de)compiler, a network specification language (MetaNet), and hardware drivers. Its requirements are based on experiences with a text based network environment, which has been in use at our department since early 1988. Using the environment requires minimal programming experience. Currently, the system is implemented only on PCs. Off-loading of calculation processes to other machines is achieved through hardware drivers. It is possible to convert MetaNet code into ANSI C for direct compilation to stand-alone applications on any machine.
[1] Gezinus Wolters,et al. Novelty Dependent Categorization and Learning in Calm Modules , 1990 .
[2] R. H. Phaf,et al. CALM networks: a modular approach to supervised and unsupervised learning , 1989, International 1989 Joint Conference on Neural Networks.