Predictive Coding beyond Correlations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Salvatori, Tommaso, Pinchetti, Luca, M'Charrak, Amine, Millidge, Beren, Lukasiewicz, Thomas
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910468231135232
author Salvatori, Tommaso
Pinchetti, Luca
M'Charrak, Amine
Millidge, Beren
Lukasiewicz, Thomas
author_facet Salvatori, Tommaso
Pinchetti, Luca
M'Charrak, Amine
Millidge, Beren
Lukasiewicz, Thomas
contents Recently, there has been extensive research on the capabilities of biologically plausible algorithms. In this work, we show how one of such algorithms, called predictive coding, is able to perform causal inference tasks. First, we show how a simple change in the inference process of predictive coding enables to compute interventions without the need to mutilate or redefine a causal graph. Then, we explore applications in cases where the graph is unknown, and has to be inferred from observational data. Empirically, we show how such findings can be used to improve the performance of predictive coding in image classification tasks, and conclude that such models are able to perform simple end-to-end causal inference tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2306_15479
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Predictive Coding beyond Correlations
Salvatori, Tommaso
Pinchetti, Luca
M'Charrak, Amine
Millidge, Beren
Lukasiewicz, Thomas
Machine Learning
Recently, there has been extensive research on the capabilities of biologically plausible algorithms. In this work, we show how one of such algorithms, called predictive coding, is able to perform causal inference tasks. First, we show how a simple change in the inference process of predictive coding enables to compute interventions without the need to mutilate or redefine a causal graph. Then, we explore applications in cases where the graph is unknown, and has to be inferred from observational data. Empirically, we show how such findings can be used to improve the performance of predictive coding in image classification tasks, and conclude that such models are able to perform simple end-to-end causal inference tasks.
title Predictive Coding beyond Correlations
topic Machine Learning
url https://arxiv.org/abs/2306.15479