Abstract | ||
---|---|---|
Differential geometry is used to investigate the structure of neural-network-based control systems. The key aspect is relative order-an invariant property of dynamic systems. Finite relative order allows the specification of a minimal architecture for a recurrent network. Any system with finite relative order has a left inverse. It is shown that a recurrent network with finite relative order has a local inverse that is also a recurrent network with the same weights. The results have implications for the use of recurrent networks in the inverse-model-based control of nonlinear systems. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1016/0005-1098(95)00098-4 | Automatica (Journal of IFAC) |
Keywords | Field | DocType |
recurrent network,relative order | Inverse,Nonlinear system,Control theory,Invariant (mathematics),Differential geometry,Control system,Artificial neural network,Dynamical system,Mathematics | Journal |
Volume | Issue | ISSN |
32 | 1 | 0005-1098 |
Citations | PageRank | References |
3 | 0.82 | 2 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
C. Kambhampati | 1 | 54 | 10.68 |
S. Manchanda | 2 | 4 | 1.17 |
a e delgado | 3 | 3 | 0.82 |
G. G. R. Green | 4 | 3 | 0.82 |
Kevin Warwick | 5 | 129 | 21.37 |
Ming T. Tham | 6 | 32 | 4.77 |