Dynamically Adapting Floating-Point Precision to Accelerate Deep Neural Network Training

التفاصيل البيبلوغرافية
العنوان: Dynamically Adapting Floating-Point Precision to Accelerate Deep Neural Network Training
المؤلفون: Rios, John Osorio, Armejach, Adria, Petit, Eric, Henry, Greg, Casas, Marc
المصدر: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) ICMLA Machine Learning and Applications (ICMLA), 2021 20th IEEE International Conference on. :980-987 Dec, 2021
Relation: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)
قاعدة البيانات: IEEE Xplore Digital Library
الوصف
ردمك:9781665443371
DOI:10.1109/ICMLA52953.2021.00161