Time Series Forecasting

Perform time series forecasting in Amazon SageMaker

SageMaker Algorithm	CPU Training	GPU Training	Multi-GPU Training	Incremental Training
CfC

CfC SageMaker Algorithm

The CfC SageMaker Algorithm performs time series forecasting with the Closed-Form Continuous-Depth (CfC) network. CfCs are continuous-time recurrent neural networks which implement an approximate closed-form solution of the Liquid Time Constant (LTC) ordinary differential equation. CfCs are also referred to as Liquid Neural Networks. The algorithm can be used for both univariate and multivariate time series and supports the inclusion of external features. For additional information, see the algorithm's AWS Marketplace listing page and GitHub repository.