Article

Shared Representations of Stability in Humans, Supervised & Unsupervised Deep Neural Networks

2021-03-05

Abstract excerpt

<p>At a glance, the human visual system transforms complex retinal images into generic feature representations useful for guiding a wide range of behaviors. Here, we provide evidence that the feature representations embedded in purely feed- forward neural networks are sufficient to explain seemingly high-level human judgments: in this case, the stability of randomly arranged block towers. To do this, we first show...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 03b9ae43-e76c-5177-8e4a-2fc06142edbe
DOI: 10.31234/osf.io/eyqb4

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Shared Representations of Stability in Humans, Supervised & Unsupervised Deep Neural NetworksDOI 10.31234/osf.io/eyqb4Read

Invariant representation of physical stability in the human brainSemantic proximity Read

Deep neural networks are not a single hypothesis but a language for expressing computational hypothesesSemantic proximity Read

AI-discovered tuning laws explain neuronal population code geometrySemantic proximity Read

Predicting the partition of behavioral variability in speed perception with naturalistic stimuliSemantic proximity Read

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural NetworksSemantic proximity Read

Distinct regimes of spatial prediction across the visual field during natural visionSemantic proximity Read

A single dynamical property can account for the capacity to learn, from artificial networks to the mammalian brainSemantic proximity Read

Abstract representations emerge naturally in neural networks trained to perform multiple tasksSemantic proximity Read

A controller-peripheral architecture and costly energy principle for learningSemantic proximity Read

Deep networks may capture biological behaviour for shallow, but not deep, empirical characterizationsSemantic proximity Read

Artificial observers and real individual differences: A roadmap for a computational psychometrics of visionSemantic proximity Read

Deep Problems with Neural Network Models of Human VisionSemantic proximity Read