Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Powiadomienia systemowe
  • Sesja wygasła!

Znaleziono wyników: 3

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  gradient regularization
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
Regularizing the gradient norm of the output of a neural network is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve classification accuracy on vision tasks, using modern deep neural networks, especially when the amount of training data is small. We introduce our regularizers as members of a broader class of Jacobian-based regularizers. We demonstrate empirically on real and synthetic data that the learning process leads to gradients controlled beyond the training points, and results in solutions that generalize well.
EN
The paper deals with the numerical simulation of strain localization in granular two-phase material. A gradient enhancement of modified Cam-clay model is introduced to overcome the problem of spurious discretization sensitivity of finite element solution. Two- and three-field finite elements implemented in the finite element analysis program (FEAP) are used in numerical simulations. The attention is focused on imperfection sensitivity of shear banding simulations. An application of the modelling framework to the slope stability problem is also included.
EN
The influence of fluid phase on soil instabilities is investigated using the modified Cam-clay model within a two-phase description. Spurious mesh dependence of finite element results is prevented by a gradient enhancement of the model. The results of numerical tests for one-phase and two-phase model are compared. The influence of permeability on the stabilizing role of the fluid phase is assessed.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.