On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory | Paper Citation Record

Observation 99c0ba41-44c4-49ec-8c72-9e6a8b868046 · outbound

This paper cites Progress and limitations of deep networks to recognize objects in unusual poses.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Progress and limitations of deep networks to recognize objects in unusual poses

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.078284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91c77d72-29bf-4b10-b8a5-c1a21e7e0cc7 · outbound

This paper cites Git Re-Basin : Merging models modulo permutation symmetries.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Git Re-Basin : Merging models modulo permutation symmetries

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.081888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eff5d19-d315-4447-a3d1-91efc2cb078b · outbound

This paper cites Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.085377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84ef3a2c-0f55-4b57-a86c-5a84f61b0bbf · outbound

This paper cites Symmetry-adapted representation learning.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Symmetry-adapted representation learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.089394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04055fbf-d18f-47d6-b301-d1f781cb3a56 · outbound

This paper cites Data symmetries and learning in fully connected neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Data symmetries and learning in fully connected neural networks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.093008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7bc6831-1d3a-42cb-ba85-eab475ccc1c1 · outbound

This paper cites On exact computation with an infinitely wide neural net.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory On exact computation with an infinitely wide neural net

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.096568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e332fa0-b588-437e-b87b-6a96064ca3d9 · outbound

This paper cites Unified theoretical framework for wide neural network learning dynamics.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unified theoretical framework for wide neural network learning dynamics

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.100438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 255ec48a-9027-455d-8348-11010709fabd · outbound

This paper cites Why do deep convolutional networks generalize so poorly to small image transformations? Journal of Machine Learning Research (JMLR), 2019.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Why do deep convolutional networks generalize so poorly to small image transformations? Journal of Machine Learning Research (JMLR), 2019

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.103729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2c36cb-664c-4011-adba-2374f5171d56 · outbound

This paper cites Breaking the curse of dimensionality with convex neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Breaking the curse of dimensionality with convex neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.107011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d530f323-de98-4332-99c0-49409f0b9083 · outbound

This paper cites Explaining neural scaling laws.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Explaining neural scaling laws

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.110441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d4f3c56-b38a-4229-897a-bf73c4141171 · outbound

This paper cites A cookbook of self-supervised learning.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory A cookbook of self-supervised learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.113761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf2afc5-9cfb-4ed8-832e-23ad5c5bc70c · outbound

This paper cites Developmental changes in children’s object insertions during play.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Developmental changes in children’s object insertions during play

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.120736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d0f584f-db43-47d2-99b1-300683e365c1 · outbound

This paper cites B-spline CNNs on Lie groups.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory B-spline CNNs on Lie groups

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.124731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b05e403-b7ba-4218-8dc7-a36471543766 · outbound

This paper cites Learning invariances in neural networks from training data.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Learning invariances in neural networks from training data

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.127875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e9eeb3d-15f6-4a65-a0e1-fedf8f74e485 · outbound

This paper cites Self-consistent dynamical field theory of kernel evolution in wide neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Self-consistent dynamical field theory of kernel evolution in wide neural networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.131180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50e0573-5cba-4a0e-bc9d-a9210678dbab · outbound

This paper cites Spectrum dependent learning curves in kernel regression and wide neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Spectrum dependent learning curves in kernel regression and wide neural networks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.134366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e272fc91-5c69-4621-b34a-9039f2b80bfc · outbound

This paper cites Addressing the topological defects of disentanglement via distributed operators.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Addressing the topological defects of disentanglement via distributed operators

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.137940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96da175b-420c-4713-b59b-e016ae7ef9fd · outbound

This paper cites Does equivariance matter at scale? arXiv preprint, 2024.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Does equivariance matter at scale? arXiv preprint, 2024

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.141606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 499c2ec1-4b2d-481e-bc6e-799badd07225 · outbound

This paper cites Bronstein, Joan Bruna, Taco Cohen, and Petar Veličković.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Bronstein, Joan Bruna, Taco Cohen, and Petar Veličković

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.144909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d768c008-6a5d-4bc3-ae5c-f7d1d258c479 · outbound

This paper cites Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.148484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48a8c98a-fe6f-4911-9e23-863d563e3596 · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.151804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70946239-de03-44ce-8f5c-e466dce4f36c · outbound

This paper cites Deep reasoning networks for unsupervised pattern de-mixing with constraint reasoning.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Deep reasoning networks for unsupervised pattern de-mixing with constraint reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.155142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ec9fc66-3808-488e-ab94-cfdcaaa651e6 · outbound

This paper cites Chirikjian and Alexander B.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Chirikjian and Alexander B

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.158711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88fc3fc9-047b-461e-994d-069fb865626a · outbound

This paper cites On the global convergence of gradient descent for over-parameterized models using optimal transport.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory On the global convergence of gradient descent for over-parameterized models using optimal transport

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.161500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc0861f8-fc1f-4d27-a6de-095db5a5fd20 · outbound

This paper cites Lee, and Haim Sompolinsky.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Lee, and Haim Sompolinsky

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.164300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 071137f3-de76-4fe6-a274-d28a97866588 · outbound

This paper cites Group equivariant convolutional networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Group equivariant convolutional networks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.166999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc90508f-4520-47f7-81c2-8d494e80266c · outbound

This paper cites Gauge equivariant convolutional networks and the icosahedral CNN.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Gauge equivariant convolutional networks and the icosahedral CNN

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.169738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a65aec-b11c-4ee6-9ed5-9e46b3307d5d · outbound

This paper cites A general theory of equivariant CNNs on homogeneous spaces.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory A general theory of equivariant CNNs on homogeneous spaces

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.172929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21444cd-1d35-4da7-9c00-67746377e1b1 · outbound

This paper cites Lee, and Haim Sompolinsky.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Lee, and Haim Sompolinsky

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.175894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02dc8cb6-3608-44b7-9a6c-06a28c7b70ba · outbound

This paper cites Representing closed transformation paths in encoded network latent space.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Representing closed transformation paths in encoded network latent space

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.178660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81e592d8-6352-40d7-bb82-09e61e0d54cc · outbound

This paper cites Learning internal representations of 3D transformations from 2D projected inputs.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Learning internal representations of 3D transformations from 2D projected inputs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.181370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50644a86-4e0f-4865-9aed-dbbe19a710b3 · outbound

This paper cites Lagrangian neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Lagrangian neural networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.184033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39661d56-5209-4071-98e4-b6ce12648303 · outbound

This paper cites Learning transport operators for image manifolds.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Learning transport operators for image manifolds

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.186780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1434d68-a7c6-4439-8c75-c32c03290d1e · outbound

This paper cites Convit: Improving vision transformers with soft convolutional inductive biases.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Convit: Improving vision transformers with soft convolutional inductive biases

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.189409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69cfc71e-4f45-47aa-ba81-21367d9d25f5 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory An image is worth 16x16 words: Transformers for image recognition at scale

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.192307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6933842b-9869-4e98-b573-f4c3acc76ec2 · outbound

This paper cites Equivariant neural rendering.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Equivariant neural rendering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.195393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7faacdbd-3cb5-4062-a596-986632d5e222 · outbound

This paper cites Revisiting spatial invariance with low-rank local connectivity.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Revisiting spatial invariance with low-rank local connectivity

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.198309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b778178d-7074-494e-b81d-c93aafad77d6 · outbound

This paper cites Topological obstructions and how to avoid them.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Topological obstructions and how to avoid them

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.201089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e23ba2ef-c138-4bdb-b16f-138f5d7c925e · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.204025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b52e12f5-0558-41aa-ab0e-bcce490519b9 · outbound

This paper cites Model-agnostic meta-learning for fast adaptation of deep networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Model-agnostic meta-learning for fast adaptation of deep networks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.206823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 141aa918-48d8-47bc-b3b9-e47c79d9e88a · outbound

This paper cites Generalizing convolutional neural networks for equivariance to Lie groups on arbitrary continuous data.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Generalizing convolutional neural networks for equivariance to Lie groups on arbitrary continuous data

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.210194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08cd933c-3592-4b7c-9cb3-fb5831346b0a · outbound

This paper cites Deep learning versus kernel learning: An empirical study of loss landscape geometry and the time evolution of the neural tangent kernel.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Deep learning versus kernel learning: An empirical study of loss landscape geometry and the time evolution of the neural tangent kernel

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.213417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea684ac-23f3-48c5-8329-1e3cbcf65efb · outbound

This paper cites Learning and leveraging world models in visual representation learning.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Learning and leveraging world models in visual representation learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.216581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3dcedc-36f1-49c9-8d8a-0281be431ec0 · outbound

This paper cites Disentangling feature and lazy training in deep neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Disentangling feature and lazy training in deep neural networks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.220041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed99ced-16b8-4971-bd16-0b0996b914b4 · outbound

This paper cites Deep symmetry networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Deep symmetry networks

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.223320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4529b96-71c4-44fd-b418-00b8a7de4d3d · outbound

This paper cites Probing transfer learning with a model of synthetic correlated datasets.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Probing transfer learning with a model of synthetic correlated datasets

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.226560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cbbbb5d-3ab6-4a63-937c-2e9c444d9a6d · outbound

This paper cites Emergent equivariance in deep ensembles.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Emergent equivariance in deep ensembles

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.278978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f8cd8354-3032-48f3-bf60-eb146502a683 · outbound

This paper cites Modeling the influence of data structure on learning in neural networks: The hidden manifold model.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Modeling the influence of data structure on learning in neural networks: The hidden manifold model

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.270647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b599b688-d227-43af-900f-b0f0626f1c9d · outbound

This paper cites Hamiltonian neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Hamiltonian neural networks

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.262127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9a6d9353-23d1-4543-9ca4-6a869606a106 · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-11T14:54:53.252117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8ecece21-3cdd-4fd2-8436-f46c9ad4e647 · outbound

This paper cites The Lie derivative for measuring learned equivariance.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory The Lie derivative for measuring learned equivariance

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.242421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b9a0a97a-0600-4937-b243-d5d05e588cc0 · outbound

This paper cites Dey, Soham Mukherjee, Shreyas N.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Dey, Soham Mukherjee, Shreyas N

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.232591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 815c4505-2e9d-4901-b2d3-59c9b11de27f · outbound

This paper cites Towards a definition of disentangled representations.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Towards a definition of disentangled representations

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.222400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f2978702-18e4-4bf6-8d9a-141149d4b3e6 · outbound

This paper cites Deep networks always grok and here is why.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Deep networks always grok and here is why

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.212046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7fcc629d-e6aa-408f-b9e8-eb0cf231a596 · outbound

This paper cites Robust self-supervised learning with Lie groups.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Robust self-supervised learning with Lie groups

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.201848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4556e396-0d20-4b9c-b482-d070f6563b91 · outbound

This paper cites Morcos, and Diane Bouchacourt.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Morcos, and Diane Bouchacourt

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.191701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 09a727fe-3943-436c-ac1d-84573bf2343e · outbound

This paper cites van der Ouderaa, Gunnar R\" a tsch, Vincent Fortuin, and Mark van der Wilk.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory van der Ouderaa, Gunnar R\" a tsch, Vincent Fortuin, and Mark van der Wilk

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.181781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6392ca17-8c67-4e86-a2bd-40bc229ff358 · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Neural tangent kernel: Convergence and generalization in neural networks

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.171410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bd74e73f-0af2-424b-aa8b-60e95bfd9493 · outbound

This paper cites How DNN s break the curse of dimensionality: Compositionality and symmetry learning.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory How DNN s break the curse of dimensionality: Compositionality and symmetry learning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.160974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3ee05dfa-a5cb-461d-adb3-911a2a62b06b · outbound

This paper cites Spatial transformer networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Spatial transformer networks

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.150549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 01866553-d9b2-487c-adb3-e2c6dbb91b38 · outbound

This paper cites Symmetry breaking and equivariant neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Symmetry breaking and equivariant neural networks

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.139518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee3b96cd-c9a5-4b12-bc0c-3aa6681769bc · outbound

This paper cites Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.128853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2976c591-2772-4945-856a-d9b6a3ee94c0 · outbound

This paper cites Anderson Keller and Max Welling.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Anderson Keller and Max Welling

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.118147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2470bf8f-2e36-4450-8b9f-930323e2e1d6 · outbound

This paper cites Anderson Keller and Max Welling.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Anderson Keller and Max Welling

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.108905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c6f0bc1c-f20e-467b-a209-180cd8ff2e8c · outbound

This paper cites The formation and transformation of the perceptual world.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory The formation and transformation of the perceptual world

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.099707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d6b6140d-01b2-4338-a11d-af73ea12f322 · outbound

This paper cites LeCun, L.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory LeCun, L

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.287477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65b4ce52-7ae8-4ae1-aeb4-84ce240f9444 · outbound

This paper cites Deep neural networks as Gaussian processes.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Deep neural networks as Gaussian processes

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.083780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e26e368d-64b6-46a9-9dfd-91ca2133be81 · outbound

This paper cites How diffusion models learn to factorize and compose.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory How diffusion models learn to factorize and compose

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.073563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1574801a-3c8d-4441-abab-ca6947b47d6c · outbound

This paper cites When does compositional structure yield compositional generalization? A kernel theory.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory When does compositional structure yield compositional generalization? A kernel theory

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.063198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2b67b8d-4b50-446c-bdb0-63fedec4a090 · outbound

This paper cites When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.052656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b17b9d4a-b8db-4e5e-8d31-d34f6e34ce2f · outbound

This paper cites In-distribution adversarial attacks on object recognition models using gradient-free search.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory In-distribution adversarial attacks on object recognition models using gradient-free search

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.042030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b2365ad3-af16-4ad4-b1a4-3228c42ac43e · outbound

This paper cites Harmonics of learning: Universal fourier features emerge in invariant networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Harmonics of learning: Universal fourier features emerge in invariant networks

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.030683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bf51d45d-6181-4674-ac47-17722b53dc03 · outbound

This paper cites A mean field view of the landscape of two-layer neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory A mean field view of the landscape of two-layer neural networks

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.020263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fe864674-bbd7-4278-a65a-555d46280b27 · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-11T14:54:53.009561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a883e6ff-ed95-427a-90e0-0ac12e87b94b · outbound

This paper cites Symmetry-induced disentanglement on graphs.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Symmetry-induced disentanglement on graphs

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:53.000826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ed918246-9c34-4b25-9996-bbb878923ad7 · outbound

This paper cites Smeulders.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Smeulders

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.991902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 84bd565c-3d72-4548-a621-6d57c69bdf79 · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T14:54:52.320707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e1f539-7ffc-40ef-b785-9a46bd179881 · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-11T14:54:52.976599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ed5c878d-e734-474a-8c5f-4b693606672e · outbound

This paper cites Ensembles provably learn equivariance through data augmentation.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Ensembles provably learn equivariance through data augmentation

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.967520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2b23169f-1bd2-471c-9808-037b0cb4ee58 · outbound

This paper cites Alemi, Jascha Sohl-Dickstein, and Samuel S.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Alemi, Jascha Sohl-Dickstein, and Samuel S

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.959101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6ad189f5-450b-4aa8-94a9-5df3474beaf6 · outbound

This paper cites A comparison between humans and AI at recognizing objects in unusual poses.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory A comparison between humans and AI at recognizing objects in unusual poses

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.950263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3ffd66cc-a638-4f1b-99fc-c1be5766d393 · outbound

This paper cites Neural anisotropy directions.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Neural anisotropy directions

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.939647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bccb5c8b-6454-4338-904a-1a1442d060f2 · outbound

This paper cites Breaking the symmetry: Mirror discrimination for single letters but not for pictures in the visual word form area.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Breaking the symmetry: Mirror discrimination for single letters but not for pictures in the visual word form area

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.929916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5b40bb3-e882-479c-bcb4-8157ebd5d9a4 · outbound

This paper cites Suppression of mirror generalization for reversible letters: Evidence from masked priming.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Suppression of mirror generalization for reversible letters: Evidence from masked priming

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.918235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3a2752e8-3ca7-4c24-a364-23be8e72fe15 · outbound

This paper cites Equivariant representation learning in the presence of stabilizers.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Equivariant representation learning in the presence of stabilizers

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.908360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c7aae7d-42f3-4fa8-ad14-4e2cb492545a · outbound

This paper cites Disentangling by subspace diffusion.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Disentangling by subspace diffusion

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.898857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 392be3de-9ca3-4a13-8de8-24c3893b2518 · outbound

This paper cites Grokking: Generalization beyond overfitting on small algorithmic datasets.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Grokking: Generalization beyond overfitting on small algorithmic datasets

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.888996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 88e0556c-2f73-4fd2-a0d3-0da4f872bd32 · outbound

This paper cites Dynamic routing between capsules.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Dynamic routing between capsules

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.879542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a5d3e30a-6023-427a-8eb5-d251aeaa706a · outbound

This paper cites An analytical theory of curriculum learning in teacher-student networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory An analytical theory of curriculum learning in teacher-student networks

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.870460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b66a3000-6918-43eb-9358-f155a3b143c9 · outbound

This paper cites an unresolved cited work.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-08-11T14:54:52.861748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 86471740-040b-46c7-a0a1-eb0fe559e507 · outbound

This paper cites Saxe, James L.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Saxe, James L

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.853447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 91cd2aa6-c58b-4a94-8a39-94b7b1cbf3f7 · outbound

This paper cites u gelgen, Frederik Tr \.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory u gelgen, Frederik Tr \

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.844978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 88f7eaef-919d-4c94-9750-ad30d3b945cc · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.835540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3d251193-8efe-4dd2-b8f8-5b4de7936c91 · outbound

This paper cites The pitfalls of simplicity bias in neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory The pitfalls of simplicity bias in neural networks

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.826670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c9cd70a-9721-4c37-9dcb-b80b16da5404 · outbound

This paper cites Shepard and Jacqueline Metzler.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Shepard and Jacqueline Metzler

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.817404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dd9ebf38-52c4-45c4-a7fb-a27186c4b013 · outbound

This paper cites Investigating the nature of 3D generalization in deep neural networks.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Investigating the nature of 3D generalization in deep neural networks

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.807672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b47681c1-84dd-460b-ad2c-8dcdd6723855 · outbound

This paper cites Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.797049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fbb63719-a0b0-40a3-a35b-6d08b4968377 · outbound

This paper cites Revisiting weakly supervised pre-training of visual perception models.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Revisiting weakly supervised pre-training of visual perception models

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.787192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f38dc5d9-fb94-4373-8643-792cbdf1f385 · outbound

This paper cites Olshausen.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Olshausen

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.776617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cbb9313d-fe76-4269-bc37-bd66043d67c3 · outbound

This paper cites Neural representational geometry underlies few-shot concept learning.

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory Neural representational geometry underlies few-shot concept learning

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T14:54:52.767061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers