Google Research's open TimesFM 2.5 model lets developers forecast sales, demand, traffic, prices and other time-series data on their own hardware without training a separate model for each task. The 200-million-parameter release supports substantially longer histories than its predecessor while producing both point forecasts and optional uncertainty estimates.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.