Modeling machine learning: A cognitive economic approach

Andrew Caplin, Daniel Martin and Philip Marx

Journal of Economic Theory, 2025, vol. 224, issue C

Abstract: We investigate whether the predictions of modern machine learning algorithms are consistent with economic models of human cognition. To test these models we run an experiment in which we vary the loss function used in training a leading deep learning convolutional neural network to predict pneumonia from chest X-rays. The first cognitive economic model we test, capacity-constrained learning, corresponds with an intuitive notion of machine learning: that an algorithm chooses among a feasible set of learning strategies in order to minimize the loss function used in training. Our experiment shows systematic deviations from the testable implications of this model. Instead, we find that changes in the loss function impact learning just as they might if the algorithm was a human being who found learning costly.

Keywords: Algorithms; Artificial intelligence; Machine learning; Information frictions; Information economics; Rational inattention (search for similar items in EconPapers)
JEL-codes: D83 D91 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S002205312500016X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jetheo:v:224:y:2025:i:c:s002205312500016x

DOI: 10.1016/j.jet.2025.105970

Access Statistics for this article

Journal of Economic Theory is currently edited by A. Lizzeri and K. Shell

More articles in Journal of Economic Theory from Elsevier
Bibliographic data for series maintained by Catherine Liu ().