Machine learningTime-series forecasting
Chronos：一种用于时间序列预测的标记化基础模型
Chronos 是 Ansari 等人于 2024 年在亚马逊推出的一系列预训练概率预测模型。它通过将连续值量化为离散标记来调整语言模型范式以适应时间序列，从而能够在一个大规模异构时间序列数据集上训练标准的 Transformer 模型。其结果是一个零样本预测模型，可以在不同领域进行泛化，而无需针对特定数据集进行重新训练。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Ansari, A. F., Stella, L., Turkmen, C., Zhang, X., Mercado, P., Shen, H., et al. (2024). Chronos: Learning the language of time series. Transactions on Machine Learning Research. link ↗
如何引用本页
ScholarGate. (2026, June 2). Chronos (Tokenized Time-Series Foundation Model). ScholarGate. https://scholargate.app/zh/deep-learning/chronos
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →