Hacker News
- A decoder-only foundation model for time-series forecasting https://blog.research.google/2024/02/a-decoder-only-foundation-model-for.html 64 comments
- [R] TimesFM: A Foundational Forecasting Model Pre-Trained on 100 Billion Real-World Data Points, Delivering Unprecedented Zero-Shot Performance Across Diverse Domains https://blog.research.google/2024/02/a-decoder-only-foundation-model-for.html 14 comments machinelearning
Linked pages
- [1706.03762] Attention Is All You Need https://arxiv.org/abs/1706.03762 145 comments
- Common Crawl https://commoncrawl.org/ 85 comments
- Google Trends https://trends.google.com/trends/ 38 comments
- [2310.07820] Large Language Models Are Zero-Shot Time Series Forecasters https://arxiv.org/abs/2310.07820 29 comments
- OpenAI Platform https://web.archive.org/web/20231107193055/https:/platform.openai.com/docs/models/gpt-3-5 1 comment
- https://www.sciencedirect.com/science/article/pii/S0169207021001874 1 comment
- [2310.10688] A decoder-only foundation model for time-series forecasting https://arxiv.org/abs/2310.10688 1 comment
- [1801.10198] Generating Wikipedia by Summarizing Long Sequences https://arxiv.org/abs/1801.10198 0 comments
- Exponential smoothing - Wikipedia https://en.wikipedia.org/wiki/Exponential_smoothing 0 comments
- [2304.08424] Long-term Forecasting with TiDE: Time-series Dense Encoder https://arxiv.org/abs/2304.08424 0 comments
- Autoregressive integrated moving average - Wikipedia https://en.wikipedia.org/wiki/Autoregressive_integrated_moving_average 0 comments
Would you like to stay up to date with Computer science? Checkout Computer science
Weekly.
Related searches:
Search whole site: site:blog.research.google
Search title: A decoder-only foundation model for time-series forecasting – Google Research Blog
See how to search.