Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Predictive Uncertainty Aware Active Learning for Regression-based QoT Estimation in Optical Networks

Not Accessible

Your library or personal account may give you access

Abstract

We propose an active learning strategy for regression-model-based QoT estimation to achieve higher accuracy with fewer samples. Results show that our strategy decreases 35.8% MSE on average than traditional method with the restricted sample size.

© 2021 The Author(s)

PDF Article
More Like This
Sample Distribution Matching Based Transfer Learning for QoT Estimation in Optical Networks

Tangze Qin, Zhiqun Gu, Jiawei Zhang, Yuhang Zhou, and Yuefeng Ji
T1C.4 Asia Communications and Photonics Conference (ACP) 2021

Attention Mechanism Based Multi-Channel QoT Estimation in Optical Networks

Yuhang Zhou, Zhiqun Gu, Jiawei Zhang, and Yuefeng Ji
T4A.131 Asia Communications and Photonics Conference (ACP) 2021

Using Active Learning to Decrease Probes for QoT Estimation in Optical Networks

Dario Azzimonti, Cristina Rottondi, and Massimo Tornatore
Th1H.1 Optical Fiber Communication Conference (OFC) 2019

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.