Skip to Main content Skip to Navigation
Conference papers

Feedback Control for Online Training of Neural Networks

Abstract : Convolutional neural networks (CNNs) are commonly used for image classification tasks, raising the challenge of their application on data flows. During their training, adaptation is often performed by tuning the learning rate. Usual learning rate strategies are time-based i.e. monotonously decreasing. In this paper, we advocate switching to a performance-based adaptation, in order to improve the learning efficiency. We present E (Exponential)/PI (Proportional Integral)-Control, a conditional learning rate strategy that combines a feedback PI controller based on the CNN loss function, with an exponential control signal to smartly boost the learning and adapt the PI parameters. Stability proof is provided as well as an experimental evaluation using two state of the art image datasets (CIFAR-10 and Fashion-MNIST). Results show better performances than the related works (faster network accuracy growth reaching higher levels) and robustness of the E/PI-Control regarding its parametrization.
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Zilong ZHAO Connect in order to contact the contributor
Submitted on : Tuesday, November 19, 2019 - 11:27:36 AM
Last modification on : Wednesday, November 3, 2021 - 5:13:26 AM
Long-term archiving on: : Thursday, February 20, 2020 - 5:32:32 PM


Files produced by the author(s)




Zilong Zhao, Sophie Cerf, Bogdan Robu, Nicolas Marchand. Feedback Control for Online Training of Neural Networks. CCTA 2019 - 3rd IEEE Conference on Control Technology and Applications, Aug 2019, Hong Kong, China. ⟨10.1109/CCTA.2019.8920662⟩. ⟨hal-02115916v2⟩



Record views


Files downloads