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

Statistical Mechanics of Deep Learning

Yasaman Bahri, Jonathan Kadmon, Jeffrey Pennington, +3

Annual Review of Condensed Matter Physics

Geometric LearningDeep Neural NetworksStatistical MechanicsMachine LearningData Science +10

Localization and topology protected quantum coherence at the edge of hot matter

Yasaman Bahri, Ronen Vosk, Ehud Altman, +1

Nature Communications

Sensitivity and Generalization in Neural Networks: an Empirical Study

Roman Novak, Yasaman Bahri, Daniel A. Abolafia, +2

arXiv (Cornell University)

Artificial IntelligencePoor GeneralizationNeural Scaling LawHyperparameter EstimationEngineering +13

Dynamical Isometry and a Mean Field Theory of CNNs: How to Train\n 10,000-Layer Vanilla Convolutional Neural Networks

Lechao Xiao, Yasaman Bahri, Jascha Sohl‐Dickstein, +2

arXiv (Cornell University)

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

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

Sensitivity and Generalization in Neural Networks: an Empirical Study

Roman Novak, Yasaman Bahri, Daniel A. Abolafia, +2

arXiv (Cornell University)

Artificial IntelligencePoor GeneralizationNeural Scaling LawHyperparameter EstimationEngineering +13

Geometry of neural network loss surfaces via random matrix theory

Jeffrey Pennington, Yasaman Bahri

International Conference on Machine Learning

Spectral TheoryGeometric LearningEngineeringMachine LearningDeep Learning Works +14