Search Results for author:
Found 5 papers, 1 papers with code
Curricular and Cyclical Loss for Time Series Learning Strategy
Experiments on 3 kinds of tasks and 5 real-world datasets show the benefits of CRUCIAL for most deep learning models when learning time series.
Continuous Diagnosis and Prognosis by Controlling the Update Process of Deep Neural Networks
Continuous diagnosis and prognosis are essential for intensive care patients.
ACCTS: an Adaptive Model Training Policy for Continuous Classification of Time Series
For this demand, we propose a new concept, Continuous Classification of Time Series (CCTS), to achieve the high-accuracy classification at every time.
GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization
Each local model is learned from the local data and aligns with its distribution for customization.
TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data
In this work, we propose a novel Time Encoding (TE) mechanism.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
