We show how any dataset of any modality (time-series, images, sound...) can
be approximated by a well-behaved (continuous, differentiable...) scalar
function with a single real-valued parameter. Building upon elementary concepts
from chaos theory, we adopt a pedagogical approach demonstrating how to adjust
this parameter in order to achieve arbitrary precision fit to all samples of
the data. Targeting an audience of data scientists with a taste for the curious
and unusual, the results presented here expand on previous similar observations
regarding expressiveness power and generalization of machine learning models.
Description
Real numbers, data science and chaos: How to fit any dataset with a single parameter
%0 Generic
%1 boue2019numbers
%A Boué, Laurent
%D 2019
%K data fitting parameter
%T Real numbers, data science and chaos: How to fit any dataset with a
single parameter
%U http://arxiv.org/abs/1904.12320
%X We show how any dataset of any modality (time-series, images, sound...) can
be approximated by a well-behaved (continuous, differentiable...) scalar
function with a single real-valued parameter. Building upon elementary concepts
from chaos theory, we adopt a pedagogical approach demonstrating how to adjust
this parameter in order to achieve arbitrary precision fit to all samples of
the data. Targeting an audience of data scientists with a taste for the curious
and unusual, the results presented here expand on previous similar observations
regarding expressiveness power and generalization of machine learning models.
@misc{boue2019numbers,
abstract = {We show how any dataset of any modality (time-series, images, sound...) can
be approximated by a well-behaved (continuous, differentiable...) scalar
function with a single real-valued parameter. Building upon elementary concepts
from chaos theory, we adopt a pedagogical approach demonstrating how to adjust
this parameter in order to achieve arbitrary precision fit to all samples of
the data. Targeting an audience of data scientists with a taste for the curious
and unusual, the results presented here expand on previous similar observations
regarding expressiveness power and generalization of machine learning models.},
added-at = {2019-06-13T13:39:02.000+0200},
author = {Boué, Laurent},
biburl = {https://www.bibsonomy.org/bibtex/2482aee6da09445227c0675c3b2b78790/felix.gif},
description = {Real numbers, data science and chaos: How to fit any dataset with a single parameter},
interhash = {5ee3b3b3976b293f2b88651b6824fb85},
intrahash = {482aee6da09445227c0675c3b2b78790},
keywords = {data fitting parameter},
note = {cite arxiv:1904.12320},
timestamp = {2019-06-13T13:39:02.000+0200},
title = {Real numbers, data science and chaos: How to fit any dataset with a
single parameter},
url = {http://arxiv.org/abs/1904.12320},
year = 2019
}