Porównaj metody

	Moirai: Uniwersalny Transformer do prognozowania szeregów czasowych	TimesFM: Model Fundacyjny Tylko z Dekoderem do Prognozowania Szeregów Czasowych
Dziedzina	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning
Rok powstania	2024	2024
Twórca	Gerald Woo et al. (Salesforce)	Abhimanyu Das et al. (Google)
Typ	Foundation model for zero-shot time-series forecasting	Pre-trained decoder-only transformer for zero-shot time-series forecasting
Źródło pierwotne	Woo, G., Liu, C., Kumar, A., Xiong, C., Savarese, S., & Sahoo, D. (2024). Unified training of universal time series forecasting transformers. ICML.	Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML.
Inne nazwy	Unified Time-Series Transformer, Universal Forecasting Transformer, MOIRAI, Evrensel Zaman Serisi Tahmin Transformatörü	Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli
Pokrewne	3	3
Podsumowanie	Moirai is a foundation model for universal time-series forecasting introduced by Gerald Woo and colleagues at Salesforce Research in 2024 and presented at ICML. The core idea is to pre-train a single large Transformer on an exceptionally diverse corpus of time-series data (LOTSA) spanning many domains and frequencies, enabling zero-shot and few-shot forecasting on unseen datasets without task-specific retraining. Moirai employs patch-based tokenization, any-variate attention, and a mixture-of-distributions output head to handle variable frequencies, multiple variates, and probabilistic prediction in a unified architecture.	TimesFM is a pre-trained foundation model for univariate time-series forecasting introduced by Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou from Google in 2024. The model adopts a decoder-only transformer architecture, similar in spirit to large language models, and is trained on a large corpus of real-world and synthetic time-series data. Its central innovation is the ability to perform accurate zero-shot forecasting across diverse domains without task-specific fine-tuning.