TY - GEN
T1 - Two-dimensional extensions of cascade correlation networks
AU - Su, Li
AU - Guan, Sheng Uei
N1 - Publisher Copyright:
© 2000 IEEE.
PY - 2000
Y1 - 2000
N2 - Dynamic neural network algorithms are used for automatic network design in order to avoid time consuming search for finding an appropriate network topology with trial and error methods. The Cascade Correlation Network is a constructive method for building network architectures automatically. We present a novel incremental cascade network architecture based on it. We also report on benchmarking results for the two-spiral problem and two real world problems. Compared with results from the original cascade correlation network, our method yields a better performance.
AB - Dynamic neural network algorithms are used for automatic network design in order to avoid time consuming search for finding an appropriate network topology with trial and error methods. The Cascade Correlation Network is a constructive method for building network architectures automatically. We present a novel incremental cascade network architecture based on it. We also report on benchmarking results for the two-spiral problem and two real world problems. Compared with results from the original cascade correlation network, our method yields a better performance.
UR - http://www.scopus.com/inward/record.url?scp=0003047313&partnerID=8YFLogxK
U2 - 10.1109/HPC.2000.846534
DO - 10.1109/HPC.2000.846534
M3 - Conference Proceeding
AN - SCOPUS:0003047313
T3 - Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000
SP - 138
EP - 141
BT - Proceedings - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000
Y2 - 14 May 2000 through 17 May 2000
ER -