A decoder-only foundation model for time-series forecasting - Google Research Blog

Retrieved on: 2024-02-02 19:41:41

Tags for this article:

Large language models

Deep learning

Natural language processing

OpenAI

Statistical forecasting

Transformer

Forecasting

Prompt engineering

Generative pre-trained transformer

GPT-3

Demand forecasting

Neural machine translation

Rajat

Yichen Zhou

Click the tags to see associated articles and topics

A decoder-only foundation model for time-series forecasting - Google Research Blog. View article details on HISWAI: https://blog.research.google/2024/02/a-decoder-only-foundation-model-for.html

Excerpt

Compared to the latest large language models (LLMs), TimesFM is much smaller (200M parameters), yet we show that even at such scales, its zero-shot ...

Article found on: blog.research.google

View Original Article