|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
1991 Third IEEE Symposium on Parallel and Distributed Processing
A parallel hybrid learning approach to artificial neural nets
Dallas, Texas USA
December 02-December 05
ISBN: 0-8186-2310-1
| ASCII Text | x | ||
| Heistermann, "A parallel hybrid learning approach to artificial neural nets," Parallel and Distributed Processing, IEEE Symposium on, pp. 542-545, 1991 Third IEEE Symposium on Parallel and Distributed Processing, 1991. | |||
| BibTex | x | ||
| @article{ 10.1109/SPDP.1991.218252, author = { Heistermann}, title = {A parallel hybrid learning approach to artificial neural nets}, journal ={Parallel and Distributed Processing, IEEE Symposium on}, volume = {0}, year = {1991}, isbn = {0-8186-2310-1}, pages = {542-545}, doi = {http://doi.ieeecomputersociety.org/10.1109/SPDP.1991.218252}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Parallel and Distributed Processing, IEEE Symposium on TI - A parallel hybrid learning approach to artificial neural nets SN - 0-8186-2310-1 SP542 EP545 A1 - Heistermann, PY - 1991 KW - genetic algorithms KW - parallel hybrid learning approach KW - artificial neural nets KW - parallel computer architectures KW - EDS KW - European Declarative System KW - gradient descend algorithms KW - simulation environment KW - NNSIM KW - phoneme recognition VL - 0 JA - Parallel and Distributed Processing, IEEE Symposium on ER - | |||
The requirements of well chosen applications are of great importance for developing new parallel computer architectures. The algorithms presented are implemented on the EDS (European Declarative System) parallel computer. By using a hybrid approach of genetic and gradient descend algorithms in an appropriate manner the advantages of both methods are combined. It is shown how artificial neural networks can be modelled to make the application of the hybrid learning paradigm possible. This hybrid learning approach was implemented in a simulation environment (NNSIM) and compared with standard learning algorithms on a phoneme recognition example.
Index Terms:
genetic algorithms, parallel hybrid learning approach, artificial neural nets, parallel computer architectures, EDS, European Declarative System, gradient descend algorithms, simulation environment, NNSIM, phoneme recognition
Citation:
Heistermann, "A parallel hybrid learning approach to artificial neural nets," spdp, pp.542-545, 1991 Third IEEE Symposium on Parallel and Distributed Processing, 1991
Usage of this product signifies your acceptance of the Terms of Use.