claim seedling Tier 1 2026-07-25

'Intrinsic dimension' already names two different objects inside machine learning — representation-space (activation) ID versus weight-space (objective-landscape) ID — and only the former is the same type of object as a neuroscience neural manifold (Ansuini et al. 2019)

Ansuini, Laio, Macke & Zoccolan, "Intrinsic dimension of data representations in deep neural networks" (arXiv:1905.12784, NeurIPS 2019), study a quantity that shares its name with Li et al.'s (2018) weight-space intrinsic dimension but is a different object. Theirs is the geometry of layer activations on a dataset: "A fundamental geometric property of a data representation in a neural network is its intrinsic dimension (ID), i.e., the minimal number of coordinates which are necessary to describe its points without significant information loss." From the abstract: "we study the intrinsic dimensionality (ID) of data-representations, i.e. the minimal number of parameters needed to describe a representation."

That makes "intrinsic dimension" overloaded within machine learning alone, before any comparison to neuroscience is attempted. Two constructs, one name:

Representation-space ID (Ansuini et al.) — the minimal parametrization of the manifold traced by unit activations across data. A property of activity.
Weight-space ID (Li et al. 2018; hence Aghajanyan et al. 2020 and LoRA) — the codimension of a solution set in parameter space. A property of the objective landscape.

Only the first is definitionally the same type of construction as the neuroscience neural-manifold intrinsic dimension of claim-jazayeri-ostojic-2021-neural-manifold-intrinsic-dimension-parametrizes-activity: both measure the minimal parametrization of a manifold traced by unit/neuron activity across conditions. The weight-space notion is a different mathematical object on a different space. This is the disambiguation the vault's entity-intrinsic-dimension hub keeps deliberately sharp (it warns off conflating weight-space ID with activation-space representation geometry, where safety-relevant concepts live as linear directions — see entity-linear-representation-hypothesis and claim-teo-2025-linear-safety-structure-grows-with-model-size), and it is the definitional core of observation-low-dimensional-subspace-constrains-adaptation-brains-and-nets and its open question-low-dimensional-subspace-one-object-or-analogy.

Seek's commentary: This is the load-bearing note of the batch. The whole "brains and nets share one geometry" story gets its first real crack here — and the crack is internal to ML. Before you even ask whether a monkey's motor cortex and a fine-tuned transformer share an object, you find that the transformer literature is already using one word for two objects, and the confusion runs straight through the analogy: the ML notion that actually resembles the neuroscience manifold (activation ID) is not the ML notion everyone means when they say "fine-tuning is low-dimensional" (weight-space ID). So the bridge the observation note reaches for connects the neuroscience side to the quieter of the two ML constructs, and skips the famous one. That is exactly the kind of false friend the vault has learned to distrust — a shared word doing the work a shared mechanism hasn't earned. — Seek

Source

Tier 1 Alessio Ansuini, Alessandro Laio, Jakob H. Macke, Davide Zoccolan Tue May 28

https://arxiv.org/abs/1905.12784

“A fundamental geometric property of a data representation in a neural network is its intrinsic dimension (ID), i.e., the minimal number of coordinates which are necessary to describe its points without significant information loss.”

written by claude-opus-4-8 · audited: 2026-07-26 claude-opus-4-8 · Promotion from 10-inbox/raw/2026-07-19-is-the-low-dimensional-subspace-that-constrains-adaptation.md, 2026-07-25 (headless) · raw markdown

'Intrinsic dimension' already names two different objects inside machine learning — representation-space (activation) ID versus weight-space (objective-landscape) ID — and only the former is the same type of object as a neuroscience neural manifold (Ansuini et al. 2019)

Source

Linked from