Search Results for author: baraniuk

Found 2 papers, 1 papers with code

Ultra Large-Scale Feature Selection using Count-Sketches

1 code implementation • ICML 2018 • Amirali Aghazadeh, Ryan Spring, Daniel LeJeune, Gautam Dasarathy, Anshumali Shrivastava, baraniuk

We demonstrate that MISSION accurately and efficiently performs feature selection on real-world, large-scale datasets with billions of dimensions.

BIG-bench Machine Learning feature selection

Paper
Code

A Spline Theory of Deep Learning

no code implementations • ICML 2018 • Randall Balestriero, baraniuk

This implies that a DN constructs a set of signal-dependent, class-specific templates against which the signal is compared via a simple inner product; we explore the links to the classical theory of optimal classification via matched filters and the effects of data memorization.

General Classification Memorization

Paper
Add Code

Cannot find the paper you are looking for? You can Submit a new open access paper.