HOME > Detail View

Detail View

New backpropagation algorithm with type-2 fuzzy weights for neural networks [electronic resource]

New backpropagation algorithm with type-2 fuzzy weights for neural networks [electronic resource]

Material type
E-Book(소장)
Personal Author
Gaxiola, Fernando. Melin, Patricia, 1962-. Valdez, Fevrier.
Title Statement
New backpropagation algorithm with type-2 fuzzy weights for neural networks [electronic resource] / Fernando Gaxiola, Patricia Melin, Fevrier Valdez.
Publication, Distribution, etc
Cham :   Springer International Publishing :   Imprint: Springer,   2016.  
Physical Medium
1 online resource (ix, 102 p.) : ill. (some col.).
Series Statement
SpringerBriefs in applied sciences and technology,2191-530X
ISBN
9783319340876
요약
In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights. The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method. The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris biometric measure. In some experiments, noise was applied in different levels to the test data of the Mackey-Glass time series for showing that the type-2 fuzzy backpropagation approach obtains better behavior and tolerance to noise than the other methods. The optimization algorithms that were used are the genetic algorithm and the particle swarm optimization algorithm and the purpose of applying these methods was to find the optimal type-2 fuzzy inference systems for the neural network with type-2 fuzzy weights that permit to obtain the lowest prediction error.
General Note
Title from e-Book title page.  
Content Notes
Introduction.-Theory and Background -- Problem Statement an Development -- Simulations and Results -- Conclusions.
Bibliography, Etc. Note
Includes bibliographical references and index.
이용가능한 다른형태자료
Issued also as a book.  
Subject Added Entry-Topical Term
Back propagation (Artificial intelligence). Neural networks (Computer science). Fuzzy automata.
Short cut
URL
000 00000nam u2200205 a 4500
001 000046028901
005 20200601162649
006 m d
007 cr
008 200522s2016 sz a ob 001 0 eng d
020 ▼a 9783319340876
040 ▼a 211009 ▼c 211009 ▼d 211009
050 4 ▼a Q325.78
082 0 4 ▼a 006.31 ▼2 23
084 ▼a 006.31 ▼2 DDCK
090 ▼a 006.31
100 1 ▼a Gaxiola, Fernando.
245 1 0 ▼a New backpropagation algorithm with type-2 fuzzy weights for neural networks ▼h [electronic resource] / ▼c Fernando Gaxiola, Patricia Melin, Fevrier Valdez.
260 ▼a Cham : ▼b Springer International Publishing : ▼b Imprint: Springer, ▼c 2016.
300 ▼a 1 online resource (ix, 102 p.) : ▼b ill. (some col.).
490 1 ▼a SpringerBriefs in applied sciences and technology, ▼x 2191-530X
500 ▼a Title from e-Book title page.
504 ▼a Includes bibliographical references and index.
505 0 ▼a Introduction.-Theory and Background -- Problem Statement an Development -- Simulations and Results -- Conclusions.
520 ▼a In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights. The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method. The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris biometric measure. In some experiments, noise was applied in different levels to the test data of the Mackey-Glass time series for showing that the type-2 fuzzy backpropagation approach obtains better behavior and tolerance to noise than the other methods. The optimization algorithms that were used are the genetic algorithm and the particle swarm optimization algorithm and the purpose of applying these methods was to find the optimal type-2 fuzzy inference systems for the neural network with type-2 fuzzy weights that permit to obtain the lowest prediction error.
530 ▼a Issued also as a book.
538 ▼a Mode of access: World Wide Web.
650 0 ▼a Back propagation (Artificial intelligence).
650 0 ▼a Neural networks (Computer science).
650 0 ▼a Fuzzy automata.
700 1 ▼a Melin, Patricia, ▼d 1962-.
700 1 ▼a Valdez, Fevrier.
830 0 ▼a SpringerBriefs in applied sciences and technology.
856 4 0 ▼u https://oca.korea.ac.kr/link.n2s?url=http://dx.doi.org/10.1007/978-3-319-34087-6
945 ▼a KLPA
991 ▼a E-Book(소장)

Holdings Information

No. Location Call Number Accession No. Availability Due Date Make a Reservation Service
No. 1 Location Main Library/e-Book Collection/ Call Number CR 006.31 Accession No. E14022461 Availability Loan can not(reference room) Due Date Make a Reservation Service M

New Arrivals Books in Related Fields

Cartwright, Hugh M. (2021)
한국소프트웨어기술인협회. 빅데이터전략연구소 (2021)