Error-bound for the non-exact SVD-based complexity reduction of thegeneralized type hybrid neural networks with non-singleton consequents
Takacs, O.
Varkonyi-Koczy, A.R.
Dept. of Meas. & Inf. Syst., Budapest Univ. of Technol. & Econ.;
This paper appears in: Instrumentation and Measurement Technology Conference, 2001. IMTC 2001. Proceedings of the 18th IEEE
Publication Date: 2001
Volume: 3,
On page(s): 1607-1612 vol.3
Meeting Date: 05/21/2001 - 05/23/2001
Location: Budapest, Hungary
ISBN: 0-7803-6646-8
References Cited: 14
INSPEC Accession Number: 7080975
Digital Object Identifier: 10.1109/IMTC.2001.929475
Current Version Published: 2002-08-07
Abstract
The main advantage of neural networks (NNs) is that they are able
to solve complicated problems, even if the exact mathematical model is
not known. However, there is no universal method for the approximation
of the proper size of the neural networks which usually results in the
overestimation of the needed size. Therefore, the need arises to have
formal methods for the complexity reduction of neural networks. Singular
Value Decomposition (SVD) based complexity reduction was first proposed
for various fuzzy inference systems. Recently, the method has been
extended to generalized neural network, which made possible the use of
neural networks in time-critical systems. Beyond the elimination of
redundancy, the SVD-based reduction can be used to achieve further
reduction, if a certain amount of error can be tolerated. This paper
gives an error-bound for this further complexity reduction of
generalized type hybrid neural networks with non-singleton consequents
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
