default search action
"Infinite wide (finite depth) Neural Networks benefit from multi-task ..."
Jakob Heiss, Josef Teichmann, Hanna Wutte (2021)
- Jakob Heiss, Josef Teichmann, Hanna Wutte:
Infinite wide (finite depth) Neural Networks benefit from multi-task learning unlike shallow Gaussian Processes - an exact quantitative macroscopic characterization. CoRR abs/2112.15577 (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.