Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Woydt, Tim, Willig, Moritz, Wüst, Antonia, Helff, Lukas, Stammer, Wolfgang, Rothkopf, Constantin A., Kersting, Kristian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915735035445248
author Woydt, Tim
Willig, Moritz
Wüst, Antonia
Helff, Lukas
Stammer, Wolfgang
Rothkopf, Constantin A.
Kersting, Kristian
author_facet Woydt, Tim
Willig, Moritz
Wüst, Antonia
Helff, Lukas
Stammer, Wolfgang
Rothkopf, Constantin A.
Kersting, Kristian
contents Strong meta-learning capabilities for systematic compositionality are emerging as an important skill for navigating the complex and changing tasks of today's world. However, in presenting models for robust adaptation to novel environments, it is important to refrain from making unsupported claims about the performance of meta-learning systems that ultimately do not stand up to scrutiny. While Fodor and Pylyshyn famously posited that neural networks inherently lack this capacity as they are unable to model compositional representations or structure-sensitive operations, and thus are not a viable model of the human mind, Lake and Baroni recently presented meta-learning as a pathway to compositionality. In this position paper, we critically revisit this claim and highlight limitations in the proposed meta-learning framework for compositionality. Our analysis shows that modern neural meta-learning systems can only perform such tasks, if at all, under a very narrow and restricted definition of a meta-learning setup. We therefore claim that `Fodor and Pylyshyn's legacy' persists, and to date, there is no human-like systematic compositionality learned in neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01820
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks
Woydt, Tim
Willig, Moritz
Wüst, Antonia
Helff, Lukas
Stammer, Wolfgang
Rothkopf, Constantin A.
Kersting, Kristian
Artificial Intelligence
Machine Learning
Strong meta-learning capabilities for systematic compositionality are emerging as an important skill for navigating the complex and changing tasks of today's world. However, in presenting models for robust adaptation to novel environments, it is important to refrain from making unsupported claims about the performance of meta-learning systems that ultimately do not stand up to scrutiny. While Fodor and Pylyshyn famously posited that neural networks inherently lack this capacity as they are unable to model compositional representations or structure-sensitive operations, and thus are not a viable model of the human mind, Lake and Baroni recently presented meta-learning as a pathway to compositionality. In this position paper, we critically revisit this claim and highlight limitations in the proposed meta-learning framework for compositionality. Our analysis shows that modern neural meta-learning systems can only perform such tasks, if at all, under a very narrow and restricted definition of a meta-learning setup. We therefore claim that `Fodor and Pylyshyn's legacy' persists, and to date, there is no human-like systematic compositionality learned in neural networks.
title Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.01820