Loading...
Please wait, while we are loading the content...
Similar Documents
Training product unit neural networks with genetic algorithms
| Content Provider | NASA Technical Reports Server (NTRS) |
|---|---|
| Author | Thelen, D. C. Frenzel, J. F. Janson, D. J. |
| Copyright Year | 1991 |
| Description | The training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented. |
| File Size | 491693 |
| Page Count | 8 |
| File Format | |
| Alternate Webpage(s) | http://archive.org/details/NASA_NTRS_Archive_19940013881 |
| Archival Resource Key | ark:/13960/t3421w58s |
| Language | English |
| Publisher Date | 1991-01-01 |
| Access Restriction | Open |
| Subject Keyword | Cybernetics Neural Nets Education Minima Transistors Cmos Genetic Algorithms Switching Circuits Ntrs Nasa Technical Reports Server (ntrs) Nasa Technical Reports Server Aerodynamics Aircraft Aerospace Engineering Aerospace Aeronautic Space Science |
| Content Type | Text |
| Resource Type | Article |
