29 April 2009 Concurrent evolution of feature extractors and modular artificial neural networks
Author Affiliations +
This paper presents a new approach for the design of feature-extracting recognition networks that do not require expert knowledge in the application domain. Feature-Extracting Recognition Networks (FERNs) are composed of interconnected functional nodes (feurons), which serve as feature extractors, and are followed by a subnetwork of traditional neural nodes (neurons) that act as classifiers. A concurrent evolutionary process (CEP) is used to search the space of feature extractors and neural networks in order to obtain an optimal recognition network that simultaneously performs feature extraction and recognition. By constraining the hill-climbing search functionality of the CEP on specific parts of the solution space, i.e., individually limiting the evolution of feature extractors and neural networks, it was demonstrated that concurrent evolution is a necessary component of the system. Application of this approach to a handwritten digit recognition task illustrates that the proposed methodology is capable of producing recognition networks that perform in-line with other methods without the need for expert knowledge in image processing.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Victor Hannak, Victor Hannak, Andreas Savakis, Andreas Savakis, Shanchieh Jay Yang, Shanchieh Jay Yang, Peter Anderson, Peter Anderson, "Concurrent evolution of feature extractors and modular artificial neural networks", Proc. SPIE 7347, Evolutionary and Bio-Inspired Computation: Theory and Applications III, 73470K (29 April 2009); doi: 10.1117/12.820008; https://doi.org/10.1117/12.820008

Back to Top