Abstract
The Artificial Bee Colony (ABC) is a recently introduced swarm intelligence algorithm for optimization that has previously been applied successfully to the training of neural networks. This paper explores more carefully the performance of the ABC algorithm for optimizing the connection weights of feed-forward neural networks for classification tasks, and presents a more rigorous comparison with the traditional Back-Propagation (BP) training algorithm. The empirical results show that using the standard \stopping early" approach with optimized learning parameters leads to improved BP performance over the previous comparative study, and that a simple variation of the ABC approach provides improved ABC performance too. With both improvements applied, we conclude that the ABC approach does perform very well on small problems, but the generalization performances achieved are only significantly better than standard BP on one out of six datasets, and the training times increase rapidly as the size of the problem grows.
Original language | English |
---|---|
Title of host publication | Nature Inspired Cooperative Strategies for Optimization (NICSO 2013) |
Subtitle of host publication | learning, optimization and interdisciplinary applications |
Editors | German Terrazas, Fernando E. B. Otero, Antonio D. Masegosa |
Publisher | Springer |
Pages | 191-201 |
Number of pages | 11 |
ISBN (Electronic) | 978-3-319-01692-4 |
ISBN (Print) | 9783319016917 |
Publication status | Published - 2014 |
Event | Nature Inspired Cooperative Strategies for Optimization (NICSO 2013) - , United Kingdom Duration: 2 Sept 2013 → … |
Conference
Conference | Nature Inspired Cooperative Strategies for Optimization (NICSO 2013) |
---|---|
Country/Territory | United Kingdom |
Period | 2/09/13 → … |