Abstract
Fine-tuned learning is an enhancement to the standard backpropagation algorithm that relies on the notion of data approximation followed by sequential data refinement. It appears to be a quick and accurate variant of standard backpropagation. In this paper, we conduct extensive computational testing of fine-tuned learning in order to evaluate its effectiveness in reducing processing time and avoiding early convergence to local minima. Our results show that fine-tuned learning improves the performance of standard backpropagation.
Original language | English (US) |
---|---|
Title of host publication | Intelligent Engineering Systems Through Artificial Neural Networks |
Place of Publication | Fairfield, NJ, United States |
Publisher | ASME |
Pages | 105-111 |
Number of pages | 7 |
Volume | 7 |
State | Published - 1997 |
Externally published | Yes |
Event | Proceedings of the 1997 Artificial Neural Networks in Engineering Conference, ANNIE'97 - St.Louis, MO, USA Duration: Nov 9 1997 → Nov 12 1997 |
Other
Other | Proceedings of the 1997 Artificial Neural Networks in Engineering Conference, ANNIE'97 |
---|---|
City | St.Louis, MO, USA |
Period | 11/9/97 → 11/12/97 |
ASJC Scopus subject areas
- Software