NESS: a simulation environment for behavioral design of neural networks for prediction and control

NeSS (Neural Systems Simulator) is a flexible software environment for high level simulation, specialized to analyze and model dynamic nonlinear systems for identification and control applications. The behavior of each system constituting a project is simply defined in a graphic fashion by interconnecting atomic objects (e.g., algebraic functions, neural networks). Atomic objects are generally parameterized: their optimal values can be directly fixed by the user or identified by means of suitable training procedures.