Better schedules for low precision training of deep neural networks
Sign Up to like & getrecommendations! Published in 2024 at "Machine Learning"
DOI: 10.1007/s10994-023-06480-0
Abstract: Low precision training can significantly reduce the computational overhead of training deep neural networks (DNNs). Though many such techniques exist, cyclic precision training (CPT), which dynamically adjusts precision throughout training according to a cyclic schedule,… read more here.
Keywords: precision; training; low precision; performance ... See more keywords
Accuracy of neural networks for the simulation of chaotic dynamics: precision of training data vs precision of the algorithm
Sign Up to like & getrecommendations! Published in 2020 at "Chaos"
DOI: 10.1063/5.0021264
Abstract: We explore the influence of precision of the data and the algorithm for the simulation of chaotic dynamics by neural network techniques. For this purpose, we simulate the Lorenz system with different precisions using three… read more here.
Keywords: chaotic dynamics; network; simulation chaotic; precision training ... See more keywords