Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Rushing, Bruce
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915748154179584
author Rushing, Bruce
author_facet Rushing, Bruce
contents Mixture of experts is a prediction aggregation method in machine learning that aggregates the predictions of specialized experts. This method often outperforms Bayesian methods despite the Bayesian having stronger inductive guarantees. We argue that this is due to the greater functional capacity of mixture of experts. We prove that in a limiting case of mixture of experts will have greater capacity than equivalent Bayesian methods, which we vouchsafe through experiments on non-limiting cases. Finally, we conclude that mixture of experts is a type of abductive reasoning in the Peircian sense of hypothesis construction.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17150
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction
Rushing, Bruce
Machine Learning
Artificial Intelligence
Mixture of experts is a prediction aggregation method in machine learning that aggregates the predictions of specialized experts. This method often outperforms Bayesian methods despite the Bayesian having stronger inductive guarantees. We argue that this is due to the greater functional capacity of mixture of experts. We prove that in a limiting case of mixture of experts will have greater capacity than equivalent Bayesian methods, which we vouchsafe through experiments on non-limiting cases. Finally, we conclude that mixture of experts is a type of abductive reasoning in the Peircian sense of hypothesis construction.
title Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.17150