BiTCN: Multivariate Time Series Forecasting with Convolutional Networks
Source: DeepHub IMBA This article is about 3300 words, suggested reading time is 10 minutes. This article will introduce the BiTCN model, which utilizes two Temporal Convolutional Networks (TCN) to encode past and future covariates while maintaining computational efficiency. In the field of time series forecasting, model architecture often relies on Multi-Layer Perceptron (MLP) or … Read more