1.

Record Nr.

UNINA9910254243603321

Autore

Gaxiola Fernando

Titolo

New Backpropagation Algorithm with Type-2 Fuzzy Weights for Neural Networks [[electronic resource] /] / by Fernando Gaxiola, Patricia Melin, Fevrier Valdez

Pubbl/distr/stampa

Cham : , : Springer International Publishing : , : Imprint : Springer, , 2016

ISBN

3-319-34087-5

Edizione

[1st ed. 2016.]

Descrizione fisica

1 online resource (111 p.)

Collana

SpringerBriefs in Computational Intelligence, , 2625-3704

Disciplina

006.3

Soggetti

Computational intelligence

Artificial intelligence

Computational Intelligence

Artificial Intelligence

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Note generali

Description based upon print version of record.

Nota di bibliografia

Includes bibliographical references at the end of each chapters and index.

Nota di contenuto

Introduction.-Theory and Background -- Problem Statement an Development -- Simulations and Results -- Conclusions.

Sommario/riassunto

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 รด=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.