On the impossibility of discovering a formula for primes using AI

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kolpakov, Alexander, Rocke, Aidan
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910727256670208
author Kolpakov, Alexander
Rocke, Aidan
author_facet Kolpakov, Alexander
Rocke, Aidan
contents The present work explores the theoretical limits of Machine Learning (ML) within the framework of Kolmogorov's theory of Algorithmic Probability, which clarifies the notion of entropy as Expected Kolmogorov Complexity and formalizes other fundamental concepts such as Occam's razor via Levin's Universal Distribution. As a fundamental application, we develop Maximum Entropy methods that allow us to derive the Erdős-Kac Law and Hardy-Ramanujan theorem in Probabilistic Number Theory, and establish the impossibility of discovering a formula for primes using Machine Learning via the Prime Coding Theorem.
format Preprint
id arxiv_https___arxiv_org_abs_2308_10817
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the impossibility of discovering a formula for primes using AI
Kolpakov, Alexander
Rocke, Aidan
Computational Complexity
11N05 11N05 11N05
The present work explores the theoretical limits of Machine Learning (ML) within the framework of Kolmogorov's theory of Algorithmic Probability, which clarifies the notion of entropy as Expected Kolmogorov Complexity and formalizes other fundamental concepts such as Occam's razor via Levin's Universal Distribution. As a fundamental application, we develop Maximum Entropy methods that allow us to derive the Erdős-Kac Law and Hardy-Ramanujan theorem in Probabilistic Number Theory, and establish the impossibility of discovering a formula for primes using Machine Learning via the Prime Coding Theorem.
title On the impossibility of discovering a formula for primes using AI
topic Computational Complexity
11N05 11N05 11N05
url https://arxiv.org/abs/2308.10817