Stop the war!
Остановите войну!
for scientists:
default search action
"Convergence proof for stochastic gradient descent in the training of deep ..."
Martin Hutzenthaler et al. (2021)
- Martin Hutzenthaler, Arnulf Jentzen, Katharina Pohl, Adrian Riekert, Luca Scarpa:
Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions. CoRR abs/2112.07369 (2021)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.