Differentiable Histogram with Hard-Binning
Machine Learning
2020-12-14 v1 Artificial Intelligence
Abstract
The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed differentiable approximations, which have some limitations. A differentiable histogram that directly approximates the hard-binning operation in conventional histograms is proposed. It combines the strength of existing differentiable histograms and overcomes their individual challenges. In comparison to a histogram computed using Numpy, the proposed histogram has an absolute approximation error of 0.000158.
Cite
@article{arxiv.2012.06311,
title = {Differentiable Histogram with Hard-Binning},
author = {Ibrahim Yusuf and George Igwegbe and Oluwafemi Azeez},
journal= {arXiv preprint arXiv:2012.06311},
year = {2020}
}
Comments
Accepted at Blacks in AI Workshop, NeurIPS 2020