Abstract
Central to the performance improvement of a committee relative to individual networks is the error correlation between networks in the committee. We investigated methods of achieving error independence between the networks by training the networks with different resampling sets from the original training set. The methods were tested on the sinwave artificial task and the real-world problems of hepatoma (liver cancer) and breast cancer diagnoses.
Original language | English (US) |
---|---|
Pages | 882-888 |
Number of pages | 7 |
State | Published - 1995 |
Externally published | Yes |
Event | 8th International Conference on Neural Information Processing Systems, NIPS 1995 - Denver, United States Duration: Nov 27 1995 → Dec 2 1995 |
Conference
Conference | 8th International Conference on Neural Information Processing Systems, NIPS 1995 |
---|---|
Country/Territory | United States |
City | Denver |
Period | 11/27/95 → 12/2/95 |
ASJC Scopus subject areas
- Information Systems
- Computer Networks and Communications
- Signal Processing