3 papers
cs.DC2021
Sustaining Performance While Reducing Energy Consumption: A Control Theory Approach
Eric Rutten, Sophie Cerf, Raphaël Bleuse +2
Production high-performance computing systems continue to grow in complexity and size. As applications struggle to make use of increasingly heterogeneous compute nodes, maintaining…
cs.LG2020
Event-Based Control for Online Training of Neural Networks
Zilong Zhao, Sophie Cerf, Bogdan Robu +1
Convolutional Neural Network (CNN) has become the most used method for image classification tasks. During its training the learning rate and the gradient are two key factors to tun…
cs.LG2019
Feedback Control for Online Training of Neural Networks
Zilong Zhao, Sophie Cerf, Bogdan Robu +1
Convolutional neural networks (CNNs) are commonly used for image classification tasks, raising the challenge of their application on data flows. During their training, adaptation i…