방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 전문가 혼합× | TimesFM: 시계열 예측을 위한 디코더 전용 파운데이션 모델× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2017 | 2024 |
| 창시자≠ | Shazeer, N. et al. | Abhimanyu Das et al. (Google) |
| 유형≠ | Sparse neural network architecture (conditional computation) | Pre-trained decoder-only transformer for zero-shot time-series forecasting |
| 원전≠ | Shazeer, N. et al. (2017). Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. ICLR. arXiv:1701.06538 link ↗ | Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML. link ↗ |
| 별칭≠ | Uzman Karışımı (Mixture of Experts — MoE), uzman karışımı, MoE, sparse mixture of experts | Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli |
| 관련 | 3 | 3 |
| 요약≠ | Mixture of Experts (MoE) is a sparse neural-network architecture, introduced by Shazeer and colleagues in 2017 with the sparsely-gated MoE layer, in which only a subset of expert sub-networks is activated for each input. As seen in models such as Switch Transformer and Mixtral, it holds computation cost fixed even as the total parameter count grows. | 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. |
| ScholarGate데이터셋 ↗ |
|
|