claim

active

claim:neural-networks-show-substantial-alignment-with-biological-representations-in-the-brain-driven-by-shared-task-and-data-constraints

Neural networks show substantial alignment with biological representations in the brain, driven by shared task and data constraints

Extends convergence argument to brain-machine alignment

Source paper

extracted_from

The Platonic Representation Hypothesis

(2024) · Minyoung Huh · Brian Cheung · Tongzhou Wang · Phillip Isola

Neighborhood — ranked by edge-count

Claims (1)

claim

There is a growing similarity in how datapoints are represented in different neural network models, spanning different architectures, training objectives, and data modalities
extends
Primary empirical claim of the paper

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.863
The paper's central thesis statement, presented prominently after the abstract
Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.837
The central hypothesis of the paper; the platonic representation hypothesis itself
Neural bioelectric networks achieve a critical separation of hardware and software: the same molecular substrate can instantiate different informational content based on history, enabling minds to arise from matter.claim0.834
Foundational for understanding how physiology becomes meaning; decoupling of material state from information content is prerequisite for emergence of cognitive Self.
Linear representation hypothesis: neural networks represent meaningful concepts as directions in their activation spaces.hypothesis0.815
Foundation for interpreting features as linear directions.
Ultimately, we would like to understand neural networks well enough to be able to intentionally design them.quote0.812
Vision statement in the conclusion.
Superposition hypothesis: neural networks represent more features than dimensions using almost-orthogonal directions.hypothesis0.812
Explanation for why dictionary learning can recover many more features than dimensions.
If the universality hypothesis is broadly true, it raises the exciting possibility that artificial neural networks could predict features previously unknown in biological neural networks.claim0.808
Speculative extension of universality to neuroscience, with high-low frequency detectors as a candidate prediction
Smolensky (1986) proposes that viewing a neural representation under a basis that is not aligned with individual neurons can reveal the interpretable distributed structure of the neural representations.quote0.803
Load-bearing theoretical claim providing the conceptual foundation for DAS.