The Umwelt Representation Hypothesis: Rethinking Universality
Victoria Bosch, Rowan Sommers, Adrien Doerig, Tim C Kietzmann
TLDR
This paper introduces the Umwelt Representation Hypothesis, arguing that representational alignment in brains and ANNs stems from shared ecological constraints, not universal convergence.
Key contributions
- Challenges the "Universality" claim that ANNs and brains converge on universal representations.
- Introduces the Umwelt Representation Hypothesis (URH) as an alternative explanation.
- URH posits representational alignment arises from shared ecological constraints, not a single optimum.
- Presents evidence that representational differences are systematic and adaptive, contradicting Universality.
Why it matters
This paper rethinks representational alignment in AI and neuroscience, moving beyond universal representations. It proposes alignment stems from shared ecological constraints, offering a new framework for comparing and developing AI systems.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.