Inversion of multilayer neural network with modelling error compensation (Q4355358)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1062925
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Inversion of multilayer neural network with modelling error compensation |
scientific article; zbMATH DE number 1062925 |
Statements
Inversion of multilayer neural network with modelling error compensation (English)
0 references
17 September 1997
0 references
inversion method
0 references
multilayer neural network
0 references
iterative Newton-Raphson scheme
0 references
feedforward structure
0 references
0 references
0.7954958081245422
0 references
0.761618435382843
0 references
0.7573412656784058
0 references
0.7332421541213989
0 references
0.7294562458992004
0 references
An inversion method for a multilayer neural network is developed in a systematic way, relying on the iterative Newton-Raphson scheme. The method mainly consists in the linearization of the neural network mapping, followed by the minimization of an appropriate cost function. To compensate the effect of the errors introduced by the inversion procedure, a feedforward structure is proposed; this solution is briefly compared with other principles that are currently used for compensation. Computer experiments demonstrate good numerical performances in solving inverse kinematics of redundant robots and controlling nonlinear plants.
0 references
