<ul><li>Deep learning has revolutionized time series forecasting by capturing sequence relationships.</li><li>However, training with Mean Square Error (MSE) loss often leads to over-smooth predictions.</li><li>To address this, a novel approach of tokenizing time series values and using cross-entropy loss is proposed.</li><li>The approach includes a Hierarchical Classification Auxiliary Network (HCAN) to integrate high-entropy features at different hierarchy levels.</li></ul>

Hierarchical Classification Auxiliary Network for Time Series Forecasting

Discover more