Chris Finlay
Cited by
Cited by
How to train your neural ODE: the world of Jacobian and kinetic regularization
C Finlay, JH Jacobsen, L Nurbekyan, A Oberman
International Conference on Machine Learning, 3154-3164, 2020
Are more complicated tumour control probability models better?
J Gong, MM Dos Santos, C Finlay, T Hillen
Mathematical medicine and biology: a journal of the IMA 30 (1), 1-19, 2013
From cell population models to tumor control probability: including cell cycle effects
T Hillen, GDA De VrIeS, J Gong, C Finlay
Acta Oncologica 49 (8), 1315-1323, 2010
The logbarrier adversarial attack: making effective use of decision boundary information
C Finlay, AA Pooladian, A Oberman
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
Scaleable input gradient regularization for adversarial robustness
C Finlay, AM Oberman
Machine Learning with Applications 3, 100017, 2021
Lipschitz regularized deep neural networks generalize and are adversarially robust
C Finlay, J Calder, B Abbasi, A Oberman
arXiv preprint arXiv:1808.09540, 2018
Improved robustness to adversarial examples using Lipschitz regularization of the loss
C Finlay, AM Oberman, B Abbasi
Annual ring density for lodgepole pine as derived from models for earlywood density, latewood density and latewood proportion
DF Sattler, C Finlay, JD Stewart
Forestry: An International Journal of Forest Research 88 (5), 622-632, 2015
Approximate homogenization of convex nonlinear elliptic PDEs
C Finlay, AM Oberman
Communications in Mathematical Sciences 16 (7), 1895 - 1906, 2018
Empirical confidence estimates for classification by deep neural networks
C Finlay, AM Oberman
Improved accuracy of monotone finite difference schemes on point clouds and regular grids
C Finlay, A Oberman
SIAM Journal on Scientific Computing 41 (5), A3097-A3117, 2019
Approximate homogenization of fully nonlinear elliptic PDEs: estimates and numerical results for Pucci type equations
C Finlay, AM Oberman
Journal of Scientific Computing 77 (2), 936-949, 2018
Learning normalizing flows from Entropy-Kantorovich potentials
C Finlay, A Gerolin, AM Oberman, AA Pooladian
arXiv preprint arXiv:2006.06033, 2020
A principled approach for generating adversarial images under non-smooth dissimilarity metrics
AA Pooladian, C Finlay, T Hoheisel, A Oberman
International Conference on Artificial Intelligence and Statistics, 1442-1452, 2020
Deterministic Gaussian Averaged Neural Networks
R Campbell, C Finlay, AM Oberman
arXiv preprint arXiv:2006.06061, 2020
Adversarial Boot Camp: label free certified robustness in one epoch
R Campbell, C Finlay, AM Oberman
arXiv preprint arXiv:2010.02508, 2020
Farkas layers: don't shift the data, fix the geometry
AA Pooladian, C Finlay, AM Oberman
arXiv preprint arXiv:1910.02840, 2019
Calibrated Top-1 Uncertainty estimates for classification by score based models
AM Oberman, C Finlay, A Iannantuono, T Salvador
arXiv e-prints, arXiv: 1903.09215, 2019
Supplemental materials: A principled approach for generating adversarial images under non-smooth dissimilarity metrics
AA Pooladian, C Finlay, T Hoheisel, AM Oberman
WQ4MGM: a wood quality module for the Mixedwood Growth Model
J Stewart, C Finlay, M Bokalo, D Sattler, P Comeau
The system can't perform the operation now. Try again later.
Articles 1–20