Deep Haar Scattering Networks in Pattern Recognition: A promising approach
This work addresses pattern recognition tasks like classification and regression, offering incremental improvements in specific domains.
The paper tackles pattern recognition problems using Haar scattering networks, a simple architecture with few parameters, and shows that it outperforms best available algorithms in 4 out of 18 classification tasks and is more robust than ARIMA and ETS in regression for periodic data.
The aim of this paper is to discuss the use of Haar scattering networks, which is a very simple architecture that naturally supports a large number of stacked layers, yet with very few parameters, in a relatively broad set of pattern recognition problems, including regression and classification tasks. This architecture, basically, consists of stacking convolutional filters, that can be thought as a generalization of Haar wavelets, followed by non-linear operators which aim to extract symmetries and invariances that are later fed in a classification/regression algorithm. We show that good results can be obtained with the proposed method for both kind of tasks. We have outperformed the best available algorithms in 4 out of 18 important data classification problems, and have obtained a more robust performance than ARIMA and ETS time series methods in regression problems for data with strong periodicities.