The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

shattering: Estimate the Shattering Coefficient for a Particular Dataset

The Statistical Learning Theory (SLT) provides the theoretical background to ensure that a supervised algorithm generalizes the mapping f:X -> Y given f is selected from its search space bias F. This formal result depends on the Shattering coefficient function N(F,2n) to upper bound the empirical risk minimization principle, from which one can estimate the necessary training sample size to ensure the probabilistic learning convergence and, most importantly, the characterization of the capacity of F, including its under and overfitting abilities while addressing specific target problems. In this context, we propose a new approach to estimate the maximal number of hyperplanes required to shatter a given sample, i.e., to separate every pair of points from one another, based on the recent contributions by Har-Peled and Jones in the dataset partitioning scenario, and use such foundation to analytically compute the Shattering coefficient function for both binary and multi-class problems. As main contributions, one can use our approach to study the complexity of the search space bias F, estimate training sample sizes, and parametrize the number of hyperplanes a learning algorithm needs to address some supervised task, what is specially appealing to deep neural networks. Reference: de Mello, R.F. (2019) "On the Shattering Coefficient of Supervised Learning Algorithms" <doi:10.48550/arXiv.1911.05461>; de Mello, R.F., Ponti, M.A. (2018, ISBN: 978-3319949888) "Machine Learning: A Practical Approach on the Statistical Learning Theory".

Version: 1.0.7
Imports: FNN, pdist, slam, grDevices, Ryacas, rmarkdown, pracma, e1071, graphics, NMF, stats
Suggests: testthat
Published: 2021-08-21
DOI: 10.32614/CRAN.package.shattering
Author: Rodrigo F. de Mello ORCID iD [aut, cre]
Maintainer: Rodrigo F. de Mello <mellorf at gmail.com>
License: GPL-3
NeedsCompilation: no
CRAN checks: shattering results

Documentation:

Reference manual: shattering.pdf

Downloads:

Package source: shattering_1.0.7.tar.gz
Windows binaries: r-devel: shattering_1.0.7.zip, r-release: shattering_1.0.7.zip, r-oldrel: shattering_1.0.7.zip
macOS binaries: r-release (arm64): shattering_1.0.7.tgz, r-oldrel (arm64): shattering_1.0.7.tgz, r-release (x86_64): shattering_1.0.7.tgz, r-oldrel (x86_64): shattering_1.0.7.tgz
Old sources: shattering archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=shattering to link to this page.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.