Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels
Yuanzhi Li (Stanford University)
https://simons.berkeley.edu/talks/tbd-70
Frontiers of Deep Learning
Видео Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels канала Simons Institute
https://simons.berkeley.edu/talks/tbd-70
Frontiers of Deep Learning
Видео Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels канала Simons Institute
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Sanjeev Arora - Is Optimization the Right Language to Understand Deep Learning?A law of robustness and the importance of overparametrization in deep learningGeoffrey Hinton: The Foundations of Deep LearningStefano Soatto: "Invariance and disentanglement in deep representations"The mystery of over-parametrization in neural networks Behnam NeyshaburYann LeCun: "Energy-Based Self-Supervised Learning"Michael Mahoney: "Why Deep Learning Works: Implicit Self-Regularization in Deep Neural Networks"Reconciling modern machine learning and the bias-variance trade-offYasaman Bahri - Towards an Understanding of Wide Neural NetworksFrom Classical Statistics to Modern Machine LearningImplicit Neural Representations: From Objects to 3D ScenesDeep Networks Are Kernel Machines, Pedro DomingosJascha Sohl-Dickstein: "Generalizing Hamiltonian Monte Carlo with Neural Networks"Adam Grzywaczewski | The scaling laws of AI Why neural networks continue to growSize-free Generalization Bounds for Convolutional Neural NetworksLEARNING : ERROR BASED LEARNINGYann LeCun - Graph Embedding, Content Understanding, and Self-Supervised LearningWhen Do Neural Networks Outperform Kernel Methods?Kernel Regression