SCNN 2000. I. Basic structure and features of the simulation system for cellular neural networks

In this paper the basic structure and features of SCNN 2000, a universal simulation system for cellular neural networks (CNN) is presented. Since the first presentation of SCNN (1996) the structure of the simulation system has been changed to achieve more flexibility in simulating CNN. Especially, a wider class of training algorithms including new optimization methods have been implemented. SCNN 2000 also supports several kinds of CNN hardware as mathematical coprocessors. Additionally, a new SCNN control system has been developed, including a new graphical user interface and an integrated SCNN shell to allow a more convenient working with SCNN 2000.