Application of the adaptive neuronlike network for the identification of nonlinear multidimensional objects

Summary form only given, as follows. An investigation of adaptive control systems using neuronlike networks for the optimization of multitasking control of an unknown object has revealed that identification of the unknown object should precede the main adaptation process. The adaptive neuronlike network (ANN) is used for the simulation of an 'inverted object model'. In the identification procedure a joined block composed of the unknown object and the ANN may be described by a matrix close to the identity matrix. This procedure considerably simplifies the optimization of multitasking control. A novel model of a neuronlike element with nonlinear presynaptic inhibition was introduced. Applying this model and a modified learning process makes it possible to simulate a broad class of nonlinear multidimensional objects.<>