Neural network architectures for parameter estimation of dynamical systems | Zendy

Jitendra R. Raol | Zendy; H. Madhuranath | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Neural network architectures for parameter estimation of dynamical systems

Author(s) -

Jitendra R. Raol,

H. Madhuranath

Publication year - 1996

Publication title -

iee proceedings - control theory and applications

Language(s) - English

Resource type - Journals

eISSN - 1359-7035

pISSN - 1350-2379

DOI - 10.1049/ip-cta:19960338

Subject(s) - precomputation , artificial neural network , computer science , computation , hopfield network , dynamical systems theory , estimation theory , estimation , artificial intelligence , algorithm , engineering , physics , systems engineering , quantum mechanics

Various recurrent neural network architectures for solving the problems of parameter estimation in dynamical systems are presented. The architectures based on precomputation of weight/bias information (Hopfield neural network), direct gradient computation with and without normalisation and output error method are developed. A typical computer simulation result is given

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research