Real numbers, data science and chaos: How to fit any dataset with a single parameter

04/28/2019
by   Laurent Boué, et al.
0

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.

READ FULL TEXT

page 2

page 3

research
05/16/2022

A Survey on Semantics in Automated Data Science

Data Scientists leverage common sense reasoning and domain knowledge to ...
research
03/08/2022

Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science

Data science and machine learning provide indispensable techniques for u...
research
11/29/2021

An iterative method for estimation the roots of real-valued functions

In this paper we study the recursive sequence x_n+1=x_n+f(x_n)/2 for eac...
research
01/15/2021

A General Framework for Hypercomplex-valued Extreme Learning Machines

This paper aims to establish a framework for extreme learning machines (...
research
07/06/2022

Don't overfit the history – Recursive time series data augmentation

Time series observations can be seen as realizations of an underlying dy...
research
12/15/2016

Learning binary or real-valued time-series via spike-timing dependent plasticity

A dynamic Boltzmann machine (DyBM) has been proposed as a model of a spi...
research
06/04/2021

Inferring Granger Causality from Irregularly Sampled Time Series

Continuous, automated surveillance systems that incorporate machine lear...

Please sign up or login with your details

Forgot password? Click here to reset