Fedskill: Privacy preserved interpretable skill learning via imitation
Imitation learning that replicates experts' skills via their demonstrations has shown
significant success in various decision-making tasks. However, two critical challenges still …
significant success in various decision-making tasks. However, two critical challenges still …
An enhanced spatio-temporal constraints network for anomaly detection in multivariate time series
D Ge, Z Dong, Y Cheng, Y Wu - Knowledge-Based Systems, 2024 - Elsevier
Anomaly detection using multivariate time series plays a crucial role in system security.
Conventional deep learning detection techniques mainly depend on temporal dependency …
Conventional deep learning detection techniques mainly depend on temporal dependency …
Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Things
Abstract The Internet of Federated Things (IoFT) represents a network of interconnected
systems with federated learning as the backbone, facilitating collaborative knowledge …
systems with federated learning as the backbone, facilitating collaborative knowledge …
Advancing Anomaly Detection in Time Series Data: A Knowledge Distillation Approach with LSTM Model
S Kılınç, B Çamlıdere, E Yıldız, AK Güler… - 2023 Innovations in …, 2023 - ieeexplore.ieee.org
This paper focuses on enhancing anomaly detection in time series data using deep learning
techniques. Particularly, it investigates the integration of knowledge distillation with LSTM …
techniques. Particularly, it investigates the integration of knowledge distillation with LSTM …
[图书][B] Advances in Learning to Generalize to Out-of-Distribution Data
W Zhu - 2023 - search.proquest.com
Data-driven deep models will inherit the characteristics of the training data and thus can
often successfully handle the in-distribution testing data. However, in real-life applications …
often successfully handle the in-distribution testing data. However, in real-life applications …