An object-oriented neural network language
| Autor: | Daikui Shouren Hu |
|---|---|
| Rok vydání: | 1991 |
| Předmět: |
Object-oriented programming
Artificial neural network Computer science Programming language business.industry Time delay neural network Deep learning computer.software_genre Simulation language Network simulation Cellular neural network Artificial intelligence business computer Language construct Nervous system network models |
| Zdroj: | [Proceedings] 1991 IEEE International Joint Conference on Neural Networks. |
| DOI: | 10.1109/ijcnn.1991.170357 |
| Popis: | 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. > |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|