PERFORMANCE-DRIVEN AUTONOMOUS DESIGN OF PATTERN-RECOGNITION SYSTEMS
- 1 January 1992
- journal article
- research article
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 6 (1) , 59-77
- https://doi.org/10.1080/08839519208949942
Abstract
The closed-loop design experiment described in this paper demonstrates a three-phase automated design approach to pattern recognition. The experiment generates morphological feature detectors and then uses a novel application of genetic algorithms to select cooperative sets of features to pass to a neural net classifier. The self-organizing hybrid learning approach embodied in this closed-loop design methodology is complementary to conventional artificial intelligence (AI) expert systems that utilize rule-based approaches and a specific set of design elements. This experiment is part of a study directed to emulating the nondirected processes of biological evolution. The approach we discuss is semiautomatic in that initialization of computer programs requires human experience and expertise to select representations, develop search strategies, choose performance measures, and devise resource-allocation strategies. The hope is that these tasks will become easier with experience and will provide the means to exploit parallel processing without the need to analyze or program an entire design solution.Keywords
This publication has 13 references indexed in Scilit:
- Computational resource management in supervised learning systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Automatic generation of simple morphological algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Applications of hybrid learning to automated system designPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A study of morphological feature detector complexity and character recognition ratesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic generation of binary feature detectorsIEEE Aerospace and Electronic Systems Magazine, 1989
- Vector morphology and iconic neural networksIEEE Transactions on Systems, Man, and Cybernetics, 1989
- Image Analysis Using Mathematical MorphologyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Automatic Feature Design for Optical Character Recognition Using an Evolutionary Search ProcedurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985
- Neocognitron: A neural network model for a mechanism of visual pattern recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1983