Back to Search
Start Over
Approaches to Combining Local and Evolutionary Search for Training Neural Networks: A Review and Some New Results
- Source :
- Natural Computing Series ISBN: 9783642623868
- Publication Year :
- 2003
- Publisher :
- Springer Berlin Heidelberg, 2003.
-
Abstract
- Training of neural networks by local search such as gradient-based algorithms could be difficult. This calls for the development of alternative training algorithms such as evolutionary search. However, training by evolutionary search often requires long computation time. In this chapter, we investigate the possibilities of reducing the time taken by combining the efforts of local search and evolutionary search. There are a number of attempts to combine these search strategies, but not all of them are successful. This chapter provides a critical review of these attempts. Moreover, different approaches to combining evolutionary search and local search are compared. Experimental results indicate that while the Baldwinian and the two-phase approaches are inefficient in improving the evolution process for difficult problems, the Lamarckian approach is able to speed up the training process and to improve the solution quality. In this chapter, the strength and weakness of these approaches are illustrated, and the factors affecting their efficiency and applicability are discussed.
- Subjects :
- Engineering
Speedup
Artificial neural network
business.industry
Process (engineering)
media_common.quotation_subject
Machine learning
computer.software_genre
Recurrent neural network
Genetic algorithm
Memetic algorithm
Quality (business)
Local search (optimization)
Artificial intelligence
business
computer
media_common
Subjects
Details
- ISBN :
- 978-3-642-62386-8
- ISBNs :
- 9783642623868
- Database :
- OpenAIRE
- Journal :
- Natural Computing Series ISBN: 9783642623868
- Accession number :
- edsair.doi...........e559986a0187e5d378086552eece87a6