The SAND Neurochip and Its Embedding in the MiND System

The system MiND (Multipurpose integrated Neural Device) is a tool for the development of artiicial neural network applications which integrates hardware and software components. It includes a PCI neuro{board with up to four SAND (Simple Applicable Neural Device) neuro{chips. The neuro{board accelerates feedforward networks, Radial{ Basis-Function networks, and Kohonen feature maps. There are several simple to use software layers for exploiting the neuro{board. At the bottom , there is the driver's C interface. Secondly, a number of C++ network classes are built on the C{drivers. Thirdly, comfortable simulators with graphical interfaces base on the C++ classes. These stem from a pool of \predeened" simulators provided by the MiND system. Each simulator is constituted by a network deenition written in the neural network description language CONNECT, and by an interface deenition script. The interface deenition is based on a C++ network class generated from the CONNECT deenition, and on abstract graphical user interface classes. A user can develop own network or interface deenitions. Also, the C++ network classes can be exported for integration into custom applications.