Abstract—In this article, we propose building generalpurpose
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.
Index Terms—Scattering transforms, feature extraction,
geometric learning, machine learning.
Fernando Fernandes Neto is with the University of São Paulo, São Paulo,
Brazil (e-mail: fernando_fernandes_neto@usp.br).
Cite: Fernando Fernandes Neto, "Building Function Approximators on top of Haar Scattering Networks," International Journal of Machine Learning and Computing vol. 8, no. 3, pp. 262-267, 2018.