An object-oriented neural network language

The author points out that there are many commonalities of neural network and object-oriented methodology, and gives an informal overview of the object-oriented neural network language (OONNL), specifically designed for the neurocomputer (software simulation/hardware implementation). It is a procedural and general-purpose language, which allows parallelism via the object-oriented concept. The parallelism expressible in OONNL is independent of the underlying hardware. It is easy to work, as it has few language constructs, yet it allows the definition of various kinds of neural network models and learning rules designed by the user. It has been adopted to be the simulation language of a large-scale neural network simulating system (GKD-NNSS). Its effectiveness and efficiency have been demonstrated by applications.<<ETX>>