Home ยป Google Introduces TimesFM: Cutting-Edge AI Model for Numerical Data Prediction sans Pretraining

Google Introduces TimesFM: Cutting-Edge AI Model for Numerical Data Prediction sans Pretraining

Google has released the TimesFM model, a foundational artificial intelligence model for predicting numerical data, such as when users input basic numbers, the model can predict the next value without the need for prior training data.

To train this model, Google utilizes real-world data sets of over a hundred billion, including Google Trends and Wikipedia page views, along with synthetic data that represents basic mathematical or physics models.

The performance evaluation is conducted using the Monash Forecasting Archive, which consists of tens of thousands of data records like traffic volume and weather conditions. TimesFM outperforms models that require upfront training by using zero-shot learning, even outperforming GPT-3.5 in prediction accuracy, despite its smaller model size of only 200 million parameters.

The model is available for download from HuggingFace.
Source: Google Research

TLDR: Google’s TimesFM model makes accurate numerical predictions without the need for prior training, outperforming larger models like GPT-3.5 in certain scenarios. It is available for download from HuggingFace.

More Reading

Post navigation

Leave a Comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Announcement: OpenAI Collaborates with Apple to Link ChatGPT, Assuring No Data Collection but Option for Account Integration.

Prediction by Sam Altman: AI Superintelligence on the Horizon in ‘Just a Few Thousand Days’ Ahead

Experience GPT-4 Turbo: ChatGPT paying customers unlock the power!