English

Deep Learning by Scattering

Machine Learning 2015-06-26 v2 Machine Learning

Abstract

We introduce general scattering transforms as mathematical models of deep neural networks with l2 pooling. Scattering networks iteratively apply complex valued unitary operators, and the pooling is performed by a complex modulus. An expected scattering defines a contractive representation of a high-dimensional probability distribution, which preserves its mean-square norm. We show that unsupervised learning can be casted as an optimization of the space contraction to preserve the volume occupied by unlabeled examples, at each layer of the network. Supervised learning and classification are performed with an averaged scattering, which provides scattering estimations for multiple classes.

Keywords

Cite

@article{arxiv.1306.5532,
  title  = {Deep Learning by Scattering},
  author = {Stéphane Mallat and Irène Waldspurger},
  journal= {arXiv preprint arXiv:1306.5532},
  year   = {2015}
}

Comments

10 pages, 1 figure

R2 v1 2026-06-22T00:39:01.325Z