Loading...
Please wait, while we are loading the content...
Similar Documents
Learning to train neural networks for real-world control problems
| Content Provider | NASA Technical Reports Server (NTRS) |
|---|---|
| Author | Davis Jr., L. I. Feldkamp, Lee A. Puskorius, G. V. Yuan, F. |
| Copyright Year | 1994 |
| Description | Over the past three years, our group has concentrated on the application of neural network methods to the training of controllers for real-world systems. This presentation describes our approach, surveys what we have found to be important, mentions some contributions to the field, and shows some representative results. Topics discussed include: (1) executing model studies as rehearsal for experimental studies; (2) the importance of correct derivatives; (3) effective training with second-order (DEKF) methods; (4) the efficacy of time-lagged recurrent networks; (5) liberation from the tyranny of the control cycle using asynchronous truncated backpropagation through time; and (6) multistream training for robustness. Results from model studies of automotive idle speed control serve as examples for several of these topics. |
| File Size | 36650 |
| Page Count | 1 |
| File Format | |
| Alternate Webpage(s) | http://archive.org/details/NASA_NTRS_Archive_19950018849 |
| Archival Resource Key | ark:/13960/t6b32sn49 |
| Language | English |
| Publisher Date | 1994-05-11 |
| Access Restriction | Open |
| Subject Keyword | Cybernetics Controllers Robustness Mathematics Speed Control Neural Nets Machine Learning Synchronism Ntrs Nasa Technical Reports Server (ntrs) Nasa Technical Reports Server Aerodynamics Aircraft Aerospace Engineering Aerospace Aeronautic Space Science |
| Content Type | Text |
| Resource Type | Article |
