Residual activation neural network
US5559690A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Sep 16, 1994 |
| Grant date | Sep 24, 1996 |
| Priority date | — |
| Expiry date | Sep 16, 2014 |
Classification
- Technology area (CPC Y)Emerging Cross-Sectional Technologies
- CPC primaryY10S706/906
- WIPO fieldControl
- WIPO sectorInstruments
Abstract
A plant (72) is operable to receive control inputs c(t) and provide an output y(t). The plant (72) has associated therewith state variables s(t) that are not variable. A control network (74) is provided that accurately models the plant (72). The output of the control network (74) provides a predicted output which is combined with a desired output to generate an error. This error is back propagated through an inverse control network (76), which is the inverse of the control network (74) to generate a control error signal that is input to a distributed control system (73) to vary the control inputs to the plant (72) in order to change the output y(t) to meet the desired output. The control network (74) is comprised of a first network NET 1 that is operable to store a representation of the dependency of the control variables on the state variables. The predicted result is subtracted from the actual state variable input and stored as a residual in a residual layer (102). The output of the residual layer (102) is input to a hidden layer (108) which also receives the control inputs to generate a predicted output in an output layer (106). During back propagation of error, the residual val…
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.