English

Sparsely Activated Networks: A new method for decomposing and compressing data

Machine Learning 2022-12-02 v2 Machine Learning

Abstract

Recent literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features, but without considering the description length of the representations. In this thesis, first we introduce the φ\varphi metric that evaluates unsupervised models based on their reconstruction accuracy and the degree of compression of their internal representations. We then present and define two activation functions (Identity, ReLU) as base of reference and three sparse activation functions (top-k absolutes, Extrema-Pool indices, Extrema) as candidate structures that minimize the previously defined metric φ\varphi. We lastly present Sparsely Activated Networks (SANs) that consist of kernels with shared weights that, during encoding, are convolved with the input and then passed through a sparse activation function. During decoding, the same weights are convolved with the sparse activation map and subsequently the partial reconstructions from each weight are summed to reconstruct the input. We compare SANs using the five previously defined activation functions on a variety of datasets (Physionet, UCI-epilepsy, MNIST, FMNIST) and show that models that are selected using φ\varphi have small description representation length and consist of interpretable kernels.

Keywords

Cite

@article{arxiv.1911.00400,
  title  = {Sparsely Activated Networks: A new method for decomposing and compressing data},
  author = {Paschalis Bizopoulos},
  journal= {arXiv preprint arXiv:1911.00400},
  year   = {2022}
}

Comments

PhD Thesis in Greek, 158 pages for the main text, 23 supplementary pages for the presentation. arXiv:1907.06592, arXiv:1904.13216, arXiv:1902.11122

R2 v1 2026-06-23T12:02:17.963Z