Evolving Connectionist and Hybrid Systems: Methods, Tools, Applications

Author

Kasabov, Nikola

Author_Institution

Auckland Univ. of Technol., Auckland

fYear

2007

Firstpage

3

Lastpage

3

Abstract

Evolving Connectionist Systems (ECOS) are neural network systems that develop their structure, functionality and internal representation through continuous learning from data and interaction with the environment. ECOS can also evolve through generations of populations using evolutionary computation, but the focus of the presentation is on: (1) Adaptive learning and improvement of each individual model; (2) Knowledge representation, knowledge adaptation and knowledge extraction. The learning process can be: on-line, off-line, incremental, supervised, unsupervised, active, sleep/dream, etc.

Keywords

knowledge acquisition; knowledge representation; learning (artificial intelligence); neural nets; adaptive learning; continuous learning; evolving connectionist system; incremental learning; knowledge adaptation; knowledge extraction; knowledge representation; neural network system; offline learning; online learning; unsupervised learning; Bioinformatics; Biological neural networks; Brain modeling; Computational modeling; Data mining; Evolutionary computation; Genetics; Knowledge engineering; Quantum computing; Quantum entanglement;

fLanguage

English

Publisher

ieee

Conference_Titel

Hybrid Intelligent Systems, 2007. HIS 2007. 7th International Conference on

Conference_Location

Kaiserlautern

Print_ISBN

978-0-7695-2946-2

Type

conf

DOI

10.1109/HIS.2007.74

Filename

4344016