Growing cascade correlation networks in two dimensions: A heuristic approach

L. Su, S. U. Guan*, Y. C. Yeo

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Pages (from-to)249-267
Number of pages19
JournalJournal of Intelligent Systems
Issue number4
Publication statusPublished - 2001
Externally publishedYes


  • Cascade correlation neural network
  • Fan-in number
  • Heuristic P-T
  • Propagation delay
  • Pyramid-tower architecture

Cite this