Search Results - "Baldock, Robert J. N"

  • Showing 1 - 6 results of 6
Refine Results
  1. 1

    Exploiting molecular dynamics in Nested Sampling simulations of small peptides by Burkoff, Nikolas S., Baldock, Robert J.N., Várnai, Csilla, Wild, David L., Csányi, Gábor

    Published in Computer physics communications (01-04-2016)
    “…Nested Sampling (NS) is a parameter space sampling algorithm which can be used for sampling the equilibrium thermodynamics of atomistic systems. NS has…”
    Get full text
    Journal Article
  2. 2

    Constant-pressure nested sampling with atomistic dynamics by Baldock, Robert J. N, Bernstein, Noam, Salerno, K. Michael, Pártay, Lívia B, Csányi, Gábor

    Published 16-11-2017
    “…Phys. Rev. E 96, 043311 (2017) The nested sampling algorithm has been shown to be a general method for calculating the pressure-temperature-composition phase…”
    Get full text
    Journal Article
  3. 3

    Determining pressure-temperature phase diagrams of materials by Baldock, Robert J. N, Pártay, Lívia B, Bartók, Albert P, Payne, Michael C, Csányi, Gábor

    Published 18-05-2016
    “…Phys. Rev. B 93, 174108 (2016) We extend the nested sampling algorithm to simulate materials under periodic boundary and constant pressure conditions, and show…”
    Get full text
    Journal Article
  4. 4

    Deep Learning Through the Lens of Example Difficulty by Baldock, Robert J. N, Maennel, Hartmut, Neyshabur, Behnam

    Published 17-06-2021
    “…Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a…”
    Get full text
    Journal Article
  5. 5

    Bayesian Neural Networks at Finite Temperature by Baldock, Robert J. N, Marzari, Nicola

    Published 08-04-2019
    “…We recapitulate the Bayesian formulation of neural network based classifiers and show that, while sampling from the posterior does indeed lead to better…”
    Get full text
    Journal Article
  6. 6

    What Do Neural Networks Learn When Trained With Random Labels? by Maennel, Hartmut, Alabdulmohsin, Ibrahim, Tolstikhin, Ilya, Baldock, Robert J. N, Bousquet, Olivier, Gelly, Sylvain, Keysers, Daniel

    Published 18-06-2020
    “…We study deep neural networks (DNNs) trained on natural image data with entirely random labels. Despite its popularity in the literature, where it is often…”
    Get full text
    Journal Article