An Improved Wavelet Neural Network For Classification And Function Approximation
Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this thesis, two different approaches were proposed for improving the predictive capability of WNNs. First, the types of activation functions used in the hidden layer of the WNN were...
محفوظ في:
المؤلف الرئيسي: | Ong , Pauline |
---|---|
التنسيق: | أطروحة |
اللغة: | English |
منشور في: |
2011
|
الموضوعات: | |
الوصول للمادة أونلاين: | http://eprints.usm.my/42264/1/ONG_PAULINE.pdf |
الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
مواد مشابهة
-
An Improved Training Method For Wavelet Neural Networks For Solving Ordinary And Partial Differential Equations
بواسطة: Tan, Lee Sen
منشور في: (2022) -
A Hybrid Neural Network - Hidden Markov Model - Fuzzy
Logic Method For Protein Classification
بواسطة: Chew, Martin Wooi Keat
منشور في: (2007) -
Approximate Analytical Methods For Ordinary Differential Equations Of Fractional Order
بواسطة: Alkresheh, Hytham Awad Hamad
منشور في: (2017) -
Laplace Transform With Modified Analytical Approximate Methods For Fractional Differential Equations
بواسطة: Jaber, Hailat Ibrahim Yousef
منشور في: (2022) -
The Numerical and Approximate Analytical Solution of
Parabolic Partial Differential Equations with Nonlocal
Boundary Conditions
بواسطة: Ghoreishi, Seyed Mohammad
منشور في: (2011)