no code implementations • 2 Mar 2023 • Heejeong Choi, Pilsung Kang
We propose a new time-series representation learning method by combining the advantages of self-supervised tasks related to contextual, temporal, and transformation consistency.
no code implementations • 21 Feb 2022 • Heejeong Choi, Subin Kim, Pilsung Kang
Predictive coding is further introduced to encourage the model to learn the temporal dependencies of the time series.