Wavelet neural networks: A practical guide

Created on 2023-02-28T04:08:34-06:00

Return to the Index

This card pertains to a resource available on the internet.

This card can also be read via Gemini.

Antonios K. Alexandridis, Achilleas D. Zapranis, 2013.

https://doi.org/10.1016/j.neunet.2013.01.008

WA is often regarded as a “microscope” in mathematics, (Cao, Hong, Fang, & He, 1995), and it is a powerful tool for representing nonlinearities, (Fang & Chow, 2006).

Does this mean wavelet coefficients are a way to compute non-linear values in linear space?

WNs are one hidden layer networks that use a wavelet as an activation function, instead of the classic sigmoidal family. It is important to mention here that the multidimensional wavelets preserve the “universal approximation” property that characterizes NNs. The nodes (or wavelons) of WNs are the wavelet coefficients of the function expansion that have a significant value.

TODO find the paper and read it more closely.