How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
This repository contains eight processed datasets and the codes of developed TF-C pretraining model (along with baselines) for manuscript Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency. We propose TF-C, a novel pre-training approach for learning…
The main features of mims-harvard/tfc-pretraining are: General Time Series Analysis, Time Series Foundation Models.
Projects with overlapping indexed features include: time-series-foundation-models/lag-llama — Lag-llama is a probabilistic machine learning foundation model designed for time series forecasting. It generates… damo-di-ml/neurips2023-one-fits-all — Tian Zhou, Peisong Niu, Xue Wang, Liang Sun, Rong Jin, "One Fits All: Power General Time Series Analysis by Pretrained… google-research/timesfm — TimesFM is a time series foundation model designed to generalize across diverse temporal datasets for forecasting and… huckiyang/voice2series-reprogramming — Voice2Series: Reprogramming / Prompting Acoustic Models for Time Series Classification. kimmeen/time-llm — (ICLR'24) Time-LLM: Time Series Forecasting by Reprogramming Large Language Models. amazon-science/chronos-forecasting — Chronos-forecasting is a zero-shot time series forecasting framework based on a pretrained large language model. It…
Lag-llama is a probabilistic machine learning foundation model designed for time series forecasting. It generates predictive distributions and uncertainty bounds for sequential data across arbitrary frequencies by leveraging pre-trained foundational weights. The system supports zero-shot transfer inference, allowing it to predict future values on entirely new and unseen datasets without requiring prior retraining. It achieves this by combining generalized representations from foundational training with adjustable context lengths, where historical context lengths and lagged feature values feed
Tian Zhou, Peisong Niu, Xue Wang, Liang Sun, Rong Jin, "One Fits All: Power General Time Series Analysis by Pretrained LM,", NeurIPS, 2023. paper
TimesFM is a time series foundation model designed to generalize across diverse temporal datasets for forecasting and anomaly detection. It functions as a pretrained model for predicting future values in univariate time series data, eliminating the need for manual training from scratch. The project includes a framework for adapting pretrained weights to specific datasets using low-rank adaptation to improve accuracy. It also provides specialized capabilities for integrating time-series predictions as tools within autonomous AI agent architectures and automated workflows. The system supports
Chronos-forecasting is a zero-shot time series forecasting framework based on a pretrained large language model. It enables the prediction of future values across diverse datasets without requiring task-specific training or optimization. The system functions as a probabilistic forecasting tool, producing multiple future trajectories and quantile forecasts to quantify uncertainty and potential prediction errors. It incorporates exogenous covariate integration to merge external variables and historical context into the input stream for increased precision. The project includes utilities for sy