Abstract
The application of dynamic neurons to system identification is investigated. Similar networks can easily be extended to the control of systems in an open- or closed-loop fashion. States of the dynamic neurons evolve as x = -ax+bu, where u is the input to a neuron. The output of the dynamic neurons are given by y = λ(x), where λ(.) is a nonlinear function. The Distributed Dynamic Back Propagation (DDBP) technique is used to back propagate the hierarchical-network output errors. This implementation is useful because it yields a common platform on which many identification and control problems can be investigated.
Original language | English (US) |
---|---|
Title of host publication | Intelligent Engineering Systems Through Artificial Neural Networks |
Editors | C.H. Dagli, L.I. Burke, Y.C. Shin |
Publisher | ASME |
Pages | 97-102 |
Number of pages | 6 |
Volume | 2 |
State | Published - Dec 1 1992 |
Externally published | Yes |
Event | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA Duration: Nov 15 1992 → Nov 18 1992 |
Other
Other | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 |
---|---|
City | St.Louis, MO, USA |
Period | 11/15/92 → 11/18/92 |