Publication: Evolutionary cellular configurations for designing feed-forward neural networks architectures
Loading...
Identifiers
ISSN: 1611-3349 (Online)
ISBN: 978-3-540-42235-8
Publication date
2001
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Impact
Export
Abstract
In the recent years, the interest to develop automatic methods to determine appropriate architectures of feed-forward neural networks has increased. Most of the methods are based on evolutionary computation paradigms. Some of the designed methods are based on direct representations of the parameters of the network. These representations do not allow scalability, so to represent large architectures, very large structures are required. An alternative more interesting are the indirect schemes. They codify a compact representation of the neural network. In this work, an indirect constructive encoding scheme is presented. This scheme is based on cellular automata representations in order to increase the scalability of the method.
Description
Proceeding of: 6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001 Granada, Spain, June 13–15, 2001
Keywords
Bibliographic citation
Connectionist models of neurons, learning processes, and Artificial Intelligence. Berlin: Springer, 2001. p. 514-521 (Lecture Notes in Computer Science; 2084)