Сравнение на методи

	Time-MoE: Фундаментален модел от типа „смес от експерти“ за времеви редове	TimesFM: Модел с основа за прогнозиране на времеви редове само с декодер
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2024	2024
Създател	Xiaoming Shi et al.	Abhimanyu Das et al. (Google)
Тип	Sparse mixture-of-experts autoregressive foundation model	Pre-trained decoder-only transformer for zero-shot time-series forecasting
Основополагащ източник	Shi, X., Wang, S., Nie, Y., Li, D., Ye, Z., Wen, Q., & Jin, M. (2024). Time-MoE: Billion-scale time series foundation models with mixture of experts. ICLR 2025.	Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML.
Други названия	Time Mixture-of-Experts, Time-MoE Foundation Model, Sparse Time-Series Transformer, Zaman Karışık Uzmanlar Modeli	Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli
Свързани	3	3
Резюме	Time-MoE is a billion-scale autoregressive foundation model for universal time-series forecasting, introduced by Shi et al. in 2024 and accepted at ICLR 2025. It combines a decoder-only transformer architecture with sparse Mixture-of-Experts (MoE) feed-forward layers, enabling the model to scale to billions of parameters while activating only a small subset of expert networks per token—dramatically increasing capacity without proportional compute cost.	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.