Neural networks as process controllers - Optimization aspects

Tariq Samad, Ted Su

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

Neural networks are now being extensively used as feedback controllers. We overview the basic approaches to neurocontroller development and concentrate our attention on the 'model-based neurocontrol design' approach. Controller design is viewed as an optimization problem, and a basic distinction is made between gradient-based and non-gradient-based algorithms. The former impose constraints on the design problem in order to facilitate the computational aspects of the optimization, whereas nongradient-based optimization allows for general problem formulations but at significant computational cost. The 'Parametrized Neurocontroller' concept is discussed to motivate the need for nongradient-based optimization and an evolutionary optimization algorithm is presented.

Original languageEnglish (US)
Pages (from-to)2486-2490
Number of pages5
JournalProceedings of the American Control Conference
Volume3
StatePublished - Dec 1 1994
EventProceedings of the 1994 American Control Conference. Part 1 (of 3) - Baltimore, MD, USA
Duration: Jun 29 1994Jul 1 1994

Fingerprint Dive into the research topics of 'Neural networks as process controllers - Optimization aspects'. Together they form a unique fingerprint.

Cite this