New Backpropagation Algorithm with Type-2 Fuzzy Weights for Neural Networks

Nonfiction, Computers, Advanced Computing, Artificial Intelligence, General Computing
Cover of the book New Backpropagation Algorithm with Type-2 Fuzzy Weights for Neural Networks by Fernando Gaxiola, Patricia Melin, Fevrier Valdez, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Fernando Gaxiola, Patricia Melin, Fevrier Valdez ISBN: 9783319340876
Publisher: Springer International Publishing Publication: June 2, 2016
Imprint: Springer Language: English
Author: Fernando Gaxiola, Patricia Melin, Fevrier Valdez
ISBN: 9783319340876
Publisher: Springer International Publishing
Publication: June 2, 2016
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer International Publishing

Cover of the book Multi-scale Quantitative Diagenesis and Impacts on Heterogeneity of Carbonate Reservoir Rocks by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Impact of Long-Period Ground Motions on Structural Design: A Case Study for Bucharest, Romania by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Artificial Neural Networks and Machine Learning – ICANN 2018 by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Teaching and Learning Discrete Mathematics Worldwide: Curriculum and Research by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Advances in Cryptology – CRYPTO 2017 by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Robust Modelling and Simulation by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Multiculturalism as Multimodal Communication by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Disney and the Dialectic of Desire by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book The Mathematics of Networks of Linear Systems by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Digital Business by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Group Processes by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book High Performance Computing by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Accelerator Programming Using Directives by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Implications of Open Access Repositories Quality Criteria and Features for Teachers’ TPACK Development by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
Cover of the book Luxury Selling by Fernando Gaxiola, Patricia Melin, Fevrier Valdez
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy