Deep Neural Networks as Gaussian Processes

Jaehoon Lee, Yasaman Bahri, Roman Novak, +3

arXiv (Cornell University)

Artificial IntelligenceGeometric LearningConvolutional Neural NetworkDeep Neural NetworksEngineering +12

Deep Neural Networks as Gaussian Processes

Jaehoon Lee, Yasaman Bahri, Roman Novak, +3

arXiv (Cornell University)

Artificial IntelligenceGeometric LearningConvolutional Neural NetworkDeep Neural NetworksEngineering +12

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

Roman Novak, Lechao Xiao, Jaehoon Lee, +6

arXiv (Cornell University)

Artificial IntelligenceNeural Scaling LawConvolutional Neural NetworkBayesian StatisticEngineering +13

Measuring the Effects of Data Parallelism on Neural Network Training

Christopher J. Shallue, Jaehoon Lee, Joseph M. Antognini, +3

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningComputer ArchitectureParallel Pattern Recognition +17

Explaining neural scaling laws

Yasaman Bahri, Ethan Dyer, Jared Kaplan, +2

Proceedings of the National Academy of Sciences

Artificial IntelligenceEngineeringMachine LearningSocial SciencesNeural Scaling Laws +18

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Roman Novak, Lechao Xiao, Jiri Hron, +3

International Conference on Learning Representations

Artificial IntelligenceNeural TangentsGeometric LearningEngineeringMachine Learning +11

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Roman Novak, Lechao Xiao, Jiri Hron, +4

arXiv (Cornell University)

Artificial IntelligenceNeural TangentsInteractive Colab NotebookGeometric LearningEngineering +12

Bayesian Deep Convolutional Networks with Many Channels are Gaussian\n Processes

Roman Novak, Lechao Xiao, Jaehoon Lee, +6

arXiv (Cornell University)

Finite Versus Infinite Neural Networks: an Empirical Study

Jaehoon Lee, Samuel S. Schoenholz, Jeffrey Pennington, +4

Neural Information Processing Systems

Artificial IntelligenceConvolutional Neural NetworkEngineeringMachine LearningWide Neural Networks +14

Finite Versus Infinite Neural Networks: an Empirical Study

Jaehoon Lee, Samuel S. Schoenholz, Jeffrey Pennington, +4

arXiv (Cornell University)

Artificial IntelligenceConvolutional Neural NetworkEngineeringMachine LearningWide Neural Networks +14