Identification of continuous-time dynamical systems: Neural network based algorithms and parallel implementation

Conference · Fri Dec 31 00:00:00 EST 1993

OSTI ID:54417

Farber, R M; Lapedes, A S ^[1]; Rico-Martinez, R; Kevrekidis, I G ^[2]

---

1. Los Alamos National Lab., NM (United States)
2. Princeton Univ., NJ (United States)

Time-delay mappings constructed using neural networks have proven successful in performing nonlinear system identification; however, because of their discrete nature, their use in bifurcation analysis of continuous-time systems is limited. This shortcoming can be avoided by embedding the neural networks in a training algorithm that mimics a numerical integrator. Both explicit and implicit integrators can be used. The former case is based on repeated evaluations of the network in a feedforward implementation; the latter relies on a recurrent network implementation. Here the algorithms and their implementation on parallel machines (SIMD and MIMD architectures) are discussed.

• OSTI ID: 54417
• Report Number(s): DOE/ER/25151-1-Vol.1; CONF-930331-Vol.1; TRN: 94:007584-0053
• Resource Relation: Conference: 6. Society for Industrial and Applied Mathematics (SIAM) conference on parallel processing for scientific computing, Norfolk, VA (United States), 21-24 Mar 1993; Other Information: PBD: 1993; Related Information: Is Part Of Parallel processing for scientific computing: Proceedings. Volume 1; Sincovec, R.F.; Leuze, M.R. [eds.] [Oak Ridge National Lab., TN (United States)]; Keyes, D.E. [ed.] [Yale Univ., New Haven, CT (United States)]; Petzold, L.R. [ed.] [Minnesota Univ., Minneapolis, MN (United States)]; Reed, D.A. [ed.] [Illinois Univ., Chicago, IL (United States)]; PB: 522 p.
• Country of Publication: United States
• Language: English

Related Subjects

99 MATHEMATICS
COMPUTERS
INFORMATION SCIENCE
MANAGEMENT
LAW
MISCELLANEOUS
PARALLEL PROCESSING
ALGORITHMS
NONLINEAR PROBLEMS
COMPUTERIZED SIMULATION
NEURAL NETWORKS