Search Results for author:
Found 3 papers, 0 papers with code
An axiomatized PDE model of deep neural networks
Based on the convection-diffusion equation, we design a new training method for ResNets.
A framework of deep neural networks via the solution operator of partial differential equations
To show the effectiveness for general form of PDEs, we show that several effective networks can be interpreted by our general form of PDEs and design a training method motivated by PDEs theory to train DNN models for better robustness and less chance of overfitting.
Deep Learning with Data Privacy via Residual Perturbation
Empirically, we show that residual perturbation outperforms the state-of-the-art DP stochastic gradient descent (DPSGD) in both membership privacy protection and maintaining the DL models' utility.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
