Based on a paradigm of neurons with local memory (NLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed.
|Original language||English (US)|
|Number of pages||5|
|Journal||Proceedings of the American Control Conference|
|State||Published - Jan 1 1997|
|Event||Proceedings of the 1997 American Control Conference. Part 3 (of 6) - Albuquerque, NM, USA|
Duration: Jun 4 1997 → Jun 6 1997