DocumentCode
2230825
Title
Fuzzy Boolean Networks Learning Behaviour
Author
Tomé, José Alberto ; Carvalho, João Paulo
Author_Institution
INESC-id/IST, Lisbon
fYear
2007
fDate
20-24 Oct. 2007
Firstpage
889
Lastpage
894
Abstract
In this paper one studies the learning behaviour of an entire rule base in fuzzy Boolean networks. It is analyzed the influence of a set of factors such as number of inputs per neuron, granularity of antecedent spaces and number of teaching experiments on learning effectiveness without cross influence between rules and on interpolation capabilities of the network. Both one dimensional problems and two dimensional problems are tested and results interpreted using theoretical results also presented.
Keywords
Boolean algebra; fuzzy neural nets; interpolation; knowledge based systems; learning (artificial intelligence); fuzzy Boolean networks; interpolation; learning behaviour; neuron; rule base; teaching experiments; Biological neural networks; Boolean functions; Fires; Flip-flops; Fuzzy reasoning; Fuzzy systems; Hardware; Intelligent systems; Network topology; Neurons;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Systems Design and Applications, 2007. ISDA 2007. Seventh International Conference on
Conference_Location
Rio de Janeiro
Print_ISBN
978-0-7695-2976-9
Type
conf
DOI
10.1109/ISDA.2007.72
Filename
4389720
Link To Document