Русские видео

Сейчас в тренде

Иностранные видео


Скачать с ютуб KDD 2023 - Weighted Sharpness-Aware Minimization (WSAM) в хорошем качестве

KDD 2023 - Weighted Sharpness-Aware Minimization (WSAM) 1 год назад


Если кнопки скачивания не загрузились НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием, пожалуйста напишите в поддержку по адресу внизу страницы.
Спасибо за использование сервиса savevideohd.ru



KDD 2023 - Weighted Sharpness-Aware Minimization (WSAM)

Jiadi Jiang, Ant Group This is our video presentation on Weighted Sharpness-Aware Minimization, or WSAM, a pioneering technique for deep learning optimization. WSAM enhances the Sharpness-Aware Minimization (SAM) method, which itself improved model generalization by targeting flatter minima in the loss landscape. Our video provides an engaging overview of WSAM, starting from the principles of gradient descent, through SAM, and onto WSAM. We explain complex concepts using clear language, making the material approachable for all. Through animated visuals, we illustrate how WSAM offers a greater degree of control over the optimization process, improving upon the limitations of SAM. This video is designed for anyone interested in AI, whether you're a deep learning practitioner or just curious about the field's latest advancements. We invite you to watch, learn, and join us in exploring the future of deep learning optimization.

Comments