Dataset Condensation for Time Series Classification via Dual Domain Matching

arXiv:2403.07245v1 Announce Type: new
Abstract: Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learning tasks, particularly for training a deep neural network. Recently, a technique named \textit{Dataset Condensation} has emerged as a solution to this problem. This technique generates a smaller synthetic dataset that has comparable performance to the full real dataset in downstream tasks such as classification. However, previous …

abstract arxiv challenges classification cs.lg data dataset deep learning deep neural network domain fields management network neural network research series tasks terms time series training type via