Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/56163
DC Field | Value | |
---|---|---|
dc.title | Growing cascade correlation networks in two dimensions: A heuristic approach | |
dc.contributor.author | Su, L. | |
dc.contributor.author | Guan, S.U. | |
dc.contributor.author | Yeo, Y.C. | |
dc.date.accessioned | 2014-06-17T02:51:27Z | |
dc.date.available | 2014-06-17T02:51:27Z | |
dc.date.issued | 2001 | |
dc.identifier.citation | Su, L.,Guan, S.U.,Yeo, Y.C. (2001). Growing cascade correlation networks in two dimensions: A heuristic approach. Journal of Intelligent Systems 11 (4) : 249-267. ScholarBank@NUS Repository. | |
dc.identifier.issn | 03341860 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/56163 | |
dc.description.abstract | Dynamic neural network algorithms are used for automatic network design to avoid a time-consuming search for finding an appropriate network topology with trial-and-error methods. Cascade Correlation Network (CCN) is one of the constructive methods to build network architecture automatically. CCN faces problems such as large propagation delays and high fan-in. We present a Heuristic Pyramid-Tower (HPT) neural network designed to overcome the shortcomings of CCN. Benchmarking results for the three real-world problems are reported. The simulation results show that a smaller network depth and reduced fan-in can be achieved using HPT as compared with the original CCN. | |
dc.source | Scopus | |
dc.subject | Cascade correlation neural network | |
dc.subject | Fan-in number | |
dc.subject | Heuristic P-T | |
dc.subject | Propagation delay | |
dc.subject | Pyramid-tower architecture | |
dc.type | Article | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.description.sourcetitle | Journal of Intelligent Systems | |
dc.description.volume | 11 | |
dc.description.issue | 4 | |
dc.description.page | 249-267 | |
dc.description.coden | JISYE | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.