Showing 21–40 of 45 results
/ Date/ Name
Aug 17, 2020Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalizationSep 23, 2017Combining Machine Learning and Physics to Understand Glassy SystemsNov 1, 2017Deep Neural Networks as Gaussian ProcessesOct 18, 2017A Correspondence Between Random Neural Networks and Statistical Field TheorySep 20, 2024Force field optimization by end-to-end differentiable atomistic simulationJul 19, 2022Deep equilibrium networks are sensitive to initialization statisticsFeb 21, 2019A Mean Field Theory of Batch NormalizationJun 14, 2018Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural NetworksAug 20, 2018Peptide-Spectra Matching from Weak SupervisionJan 21, 2020On the infinite width limit of neural networks with a standard parameterizationDec 9, 2019JAX, M.D.: A Framework for Differentiable PhysicsAug 21, 2020Unifying framework for strong and fragile liquids via machine learning: a study of liquid silicaNov 13, 2017Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practiceNov 4, 2016Deep Information PropagationJul 23, 2016The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy SystemsOct 28, 2020Self-assembling kinetics: Accessing a new design space via differentiable statistical-physics modelsFeb 7, 2021Tilting the playing field: Dynamical loss functions for machine learningMay 13, 2021dPV: An End-to-End Differentiable Solar-Cell SimulatorDec 8, 2023Programmable patchy particles for materials designMar 25, 2015Strain fluctuations and elastic moduli in disordered solids