Abstract
The common processes of data averaging and data snooping are evaluated in the context of neural networks. It is shown that both processes can lead to misleading results. Techniques are proposed for avoiding these problems. New guidelines for reporting performance are also recommended. These guidelines provide information about the actual distribution.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the National Conference on Artificial Intelligence |
Editors | Anon |
Publisher | AAAI |
Pages | 362-367 |
Number of pages | 6 |
State | Published - 1997 |
Event | Proceedings of the 1997 14th National Conference on Artificial Intelligence, AAAI 97 - Providence, RI, USA Duration: Jul 27 1997 → Jul 31 1997 |
Other
Other | Proceedings of the 1997 14th National Conference on Artificial Intelligence, AAAI 97 |
---|---|
City | Providence, RI, USA |
Period | 7/27/97 → 7/31/97 |
All Science Journal Classification (ASJC) codes
- Software