Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| LSTM× | TimesFM× | |
|---|---|---|
| Camp | Aprenentatge profund | Aprenentatge profund |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 1997 | 2024 |
| Autor original≠ | Hochreiter, S. & Schmidhuber, J. | Abhimanyu Das et al. (Google) |
| Tipus≠ | Recurrent neural network (gated memory cell) | Pre-trained decoder-only transformer for zero-shot time-series forecasting |
| Font seminal≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML. link ↗ |
| Àlies | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli |
| Relacionats≠ | 5 | 3 |
| Resum≠ | LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps. | 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. |
| ScholarGateConjunt de dades ↗ |
|
|