Building Function Approximators on top of Haar Scattering Networks
arXiv:1804.03236
Abstract
In this article we propose building general-purpose function approximators on top of Haar Scattering Networks. We advocate that this architecture enables a better comprehension of feature extraction, in addition to its implementation simplicity and low computational costs. We show its approximation and feature extraction capabilities in a wide range of different problems, which can be applied on several phenomena in signal processing, system identification, econometrics and other potential fields.
7 pages, 5 figures, to appear in International Journal of Machine Learning and Computing, vol. 8 number 3