DocumentCode :
2615953
Title :
Using biofunctionality as a novel learning method for intelligent agents
Author :
Homaifar, Abdollah ; Hawari, Hani ; Iran-Nejad, Asghar
Author_Institution :
Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
fYear :
2000
fDate :
2000
Firstpage :
345
Lastpage :
350
Abstract :
A learning machine envisioned for functioning in the physical world should be reasonably easy to implement. Our daily lives and experiences suggest that human-like learning systems are better suited for functioning in hard-to-navigate environments because of their high degree of flexibility. The paper applies the biofunctional model of human learning to the design and implementation of a learning machine that is effective in navigating complex environments and relatively easy to design using classifier systems. We portray in this case study how a fuzzy logic controller helps in making the system more conforming to the biofunctional model. The result is vast improvements to the learning rate and the overall efficiency of the whole system
Keywords :
fuzzy control; intelligent control; learning systems; mobile robots; path planning; pattern classification; biofunctionality; classifier systems; fuzzy logic controller; hard-to-navigate environments; human-like learning systems; intelligent agents; learning machine; learning method; learning rate; physical world; Brain modeling; Control engineering; Fuzzy logic; Genetic algorithms; Humans; Intelligent agent; Learning systems; Machine learning; NASA; Psychology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Control, 2000. Proceedings of the 2000 IEEE International Symposium on
Conference_Location :
Rio Patras
ISSN :
2158-9860
Print_ISBN :
0-7803-6491-0
Type :
conf
DOI :
10.1109/ISIC.2000.882948
Filename :
882948
Link To Document :
بازگشت