Unifying complexity science and machine learning
Frontiers in Complex Systems · 2023
DOI: 10.3389/fcpxs.2023.1235202 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Complex Systems, 2023. Verfasst von David C. Krakauer. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Templeton World Charity Foundation.
Abstract (Originalsprache)
Complexity science and machine learning are two complementary approaches to discovering and encoding regularities in irreducibly high dimensional phenomena. Whereas complexity science represents a coarse-grained paradigm of understanding, machine learning is a fine-grained paradigm of prediction. Both approaches seek to solve the “Wigner-Reversal” or the unreasonable ineffectiveness of mathematics in the adaptive domain where broken symmetries and broken ergodicity dominate. In order to integrate these paradigms I introduce the idea of “Meta-Ockham” which 1) moves minimality from the description of a model for a phenomenon to a description of a process for generating a model and 2) describes low dimensional features–schema–in these models. Reinforcement learning and natural selection are both parsimonious in this revised sense of minimal processes that parameterize arbitrarily high-dimensional inductive models containing latent, low-dimensional, regularities. I describe these models as “super-Humean” and discuss the scientic value of analyzing their latent dimensions as encoding functional schema.
Förderung
- Templeton World Charity Foundation
Zitieren
APA
Krakauer, D. C. (2023). Unifying complexity science and machine learning. Frontiers in Complex Systems. https://doi.org/10.3389/fcpxs.2023.1235202
Vancouver
Krakauer DC. Unifying complexity science and machine learning. Frontiers in Complex Systems. 2023. doi:10.3389/fcpxs.2023.1235202
BibTeX
@article{Krakauer2023,
author = {Krakauer, David C.},
title = {Unifying complexity science and machine learning},
journal = {Frontiers in Complex Systems},
year = {2023},
doi = {10.3389/fcpxs.2023.1235202}
}
EUVIMED