Doing the impossible: Why neural networks can be trained at all

v1v2 (latest)

Doing the impossible: Why neural networks can be trained at all

13 May 2018

Nathan Oken Hodas

ArXiv (abs)PDF HTML

Papers citing "Doing the impossible: Why neural networks can be trained at all"

4 / 4 papers shown

Title
Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition Jiazhi Li Wael AbdAlmageed 155 7 0 08 Nov 2021
Economic Nowcasting with Long Short-Term Memory Artificial Neural Networks (LSTM) D. Hopp AI4TS 63 35 0 15 Jun 2021
PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEsComputer Methods in Applied Mechanics and Engineering (CMAME), 2019 Xuhui Meng Zhen Li Dongkun Zhang George Karniadakis PINN AI4CE 166 503 0 23 Sep 2019
Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks P. Stinis Tobias J. Hagge A. Tartakovsky Enoch Yeung GAN AI4CE 128 33 0 22 Mar 2018