Stably unactivated neurons in ReLU neural networks

Documenti analoghi

• Multilevel Picard approximations and deep neural networks with ReLU, leaky ReLU, and softplus activation overcome the curse of dimensionality when approximating semilinear parabolic partial differential equations in $L^p$-sense
  di: Neufeld, Ariel, et al.
  Pubblicazione: (2024)
• Random ReLU Neural Networks as Non-Gaussian Processes
  di: Parhi, Rahul, et al.
  Pubblicazione: (2024)
• Injectivity of ReLU networks: perspectives from statistical physics
  di: Maillard, Antoine, et al.
  Pubblicazione: (2023)
• Depth Degeneracy in Neural Networks: Vanishing Angles in Fully Connected ReLU Networks on Initialization
  di: Jakub, Cameron, et al.
  Pubblicazione: (2023)
• Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks
  di: Liang, Luxu, et al.
  Pubblicazione: (2024)