New Backpropagation Algorithm With Type-2 Fuzzy Weights For Neural Networks (springerbriefs In Applied Sciences And Technology)
by Patricia Melin /
2016 / English / PDF
4.4 MB Download
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.
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 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 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.
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.