IEEE International Conference on Neural Networks 1988
DOI: 10.1109/icnn.1988.23885
|View full text |Cite
|
Sign up to set email alerts
|

Characteristics of the functional link net: a higher order delta rule net

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
37
0

Year Published

1992
1992
2014
2014

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 92 publications
(38 citation statements)
references
References 2 publications
0
37
0
Order By: Relevance
“…If we x the membership functions and adapt only the consequent part, then ANFIS can be viewed as a functional-link network 46], 71] where the \enhanced representations" of the input variables are obtained via the membership functions. These \enhanced representations", which take advantage of human knowledge, apparently express more insight than the functional expansion and the tensor (outer product) models 71].…”
Section: B Hybrid Learning Algorithmmentioning
confidence: 99%
“…If we x the membership functions and adapt only the consequent part, then ANFIS can be viewed as a functional-link network 46], 71] where the \enhanced representations" of the input variables are obtained via the membership functions. These \enhanced representations", which take advantage of human knowledge, apparently express more insight than the functional expansion and the tensor (outer product) models 71].…”
Section: B Hybrid Learning Algorithmmentioning
confidence: 99%
“…For a desired output, the network learns from many inputs. It is a supervised learning method, and is a generalization of the delta rule (a kind of learning rule in artificial neural network method) (Klassen et al, 1988). It requires a dataset of the desired output for many inputs, making up the training set.…”
Section: Upa-cen Relationship Simulationmentioning
confidence: 99%
“…Functional links were originally proposed as a method for providing more information to a neural network (Klassen, 1988). By applying non-linear operators to the input, the data complexity increases while the network complexity decreases.…”
Section: Vector Quantizationmentioning
confidence: 99%