finding

active

finding:early-layers-of-convolutional-neural-networks-converge-to-oriented-gabor-like-filters-shared-with-biological-visual-systems

Early layers of convolutional neural networks converge to oriented Gabor-like filters, shared with biological visual systems

Evidence that convergence to similar representations occurs in early layers across artificial and biological systems

Source paper

extracted_from

The Platonic Representation Hypothesis

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

Neighborhood — ranked by edge-count

Hypotheses (1)

hypothesis

Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaces
supports
The central hypothesis of the paper; the platonic representation hypothesis itself

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.

Oriented Gabor-like filters are common in both artificial and biological vision systems, suggesting convergence to a similar initial representational layerclaim0.871
Early evidence of cross-system representational convergence
Early layers of convolutional networks are more interchangeable than later layers across different architecturesfinding0.795
Lenc & Vedaldi finding on layer-wise alignment
Bioelectric networks discovered by evolution ~time of bacterial biofilms; served as ideal medium for scaling computation and information synthesis before neural systems.finding0.778
Evidence that pre-neural bioelectric infrastructure predates and likely precedes neurobiology; supports continuity of intelligence across substrates.
Neural networks show substantial alignment with biological representations in the brain, driven by shared task and data constraintsclaim0.777
Extends convergence argument to brain-machine alignment
Convolutional Neural Networksmethod0.772
Biologically-inspired AI architecture cited as a successful example of bioinspiration from visual cortex organization
Diverse computer vision models trained on visual recognition tasks converge to remarkably similar internal feature representations regardless of architecture, training procedure, or implementation details, closely matching the organization of animal visual cortexfinding0.765
Empirical evidence for the universality hypothesis cited as supporting the possibility of convergent consciousness-like solutions
Neural networks, trained with different objectives on different data and modalities, are converging to a shared statistical model of reality in their representation spaces.quote0.764
The paper's central thesis statement, presented prominently after the abstract
Different learning systems facing similar computational problems will converge to similar consciousness-like solutions, including potentially biological and artificial systemshypothesis0.761
Extension of the Universality Hypothesis to consciousness: if consciousness solves a well-defined computational problem, different systems will discover it independently