Trainability of ReLU networks and Data-dependent Initialization

v1v2 (latest)

Trainability of ReLU networks and Data-dependent Initialization

23 July 2019

George Karniadakis

ArXiv (abs)PDF HTML

Papers citing "Trainability of ReLU networks and Data-dependent Initialization"

5 / 5 papers shown

Title
Training Thinner and Deeper Neural Networks: Jumpstart Regularization Carles Roger Riera Molina Camilo Rey Thiago Serra Eloi Puertas O. Pujol 61 4 0 30 Jan 2022
Probabilistic bounds on neuron death in deep rectifier networks Blaine Rister D. Rubin 43 1 0 13 Jul 2020
Non-convergence of stochastic gradient descent in the training of deep neural networks Patrick Cheridito Arnulf Jentzen Florian Rossmannek 77 37 0 12 Jun 2020
Nearly Minimal Over-Parametrization of Shallow Neural Networks Armin Eftekhari Chaehwan Song Volkan Cevher 52 1 0 09 Oct 2019
Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations Vishnu Suresh Lokhande Songwong Tasneeyapant Abhay Venkatesh Sathya Ravi Vikas Singh 83 29 0 12 Sep 2019