Stop the war!
Остановите войну!
for scientists:
default search action
""Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training ..."
Andrew J. R. Simpson (2015)
- Andrew J. R. Simpson:
"Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks. CoRR abs/1509.05765 (2015)
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.