The Umwelt Representation Hypothesis: Rethinking Universality
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917422234075136 |
|---|---|
| author | Bosch, Victoria Sommers, Rowan Doerig, Adrien Kietzmann, Tim C |
| author_facet | Bosch, Victoria Sommers, Rowan Doerig, Adrien Kietzmann, Tim C |
| contents | Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. Here, we argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis (URH), proposing that alignment arises not from convergence toward a single global optimum, but from overlap in ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in ecological constraint space rather than searching for a single optimal world model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17960 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Umwelt Representation Hypothesis: Rethinking Universality Bosch, Victoria Sommers, Rowan Doerig, Adrien Kietzmann, Tim C Neurons and Cognition Machine Learning Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. Here, we argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis (URH), proposing that alignment arises not from convergence toward a single global optimum, but from overlap in ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in ecological constraint space rather than searching for a single optimal world model. |
| title | The Umwelt Representation Hypothesis: Rethinking Universality |
| topic | Neurons and Cognition Machine Learning |
| url | https://arxiv.org/abs/2604.17960 |