Graph neural networks in TensorFlow

Favorite Posted by Dustin Zelle, Software Engineer, Google Research, and Arno Eigenwillig, Software Engineer, CoreML Objects and their relationships are ubiquitous in the world around us, and relationships can be as important to understanding an object as its own attributes viewed in isolation — take for example transportation networks, production

Read More
Shared by Google AI Technology February 6, 2024

A decoder-only foundation model for time-series forecasting

Favorite Posted by Rajat Sen and Yichen Zhou, Google Research Time-series forecasting is ubiquitous in various domains, such as retail, finance, manufacturing, healthcare and natural sciences. In retail use cases, for example, it has been observed that improving demand forecasting accuracy can meaningfully reduce inventory costs and increase revenue. Deep

Read More
Shared by Google AI Technology February 2, 2024

MobileDiffusion: Rapid text-to-image generation on-device

Favorite Posted by Yang Zhao, Senior Software Engineer, and Tingbo Hou, Senior Staff Software Engineer, Core ML Text-to-image diffusion models have shown exceptional capabilities in generating high-quality images from text prompts. However, leading models feature billions of parameters and are consequently expensive to run, requiring powerful desktops or servers (e.g.,

Read More
Shared by Google AI Technology January 31, 2024

Advancements in machine learning for machine learning

Favorite Posted by Phitchaya Mangpo Phothilimthana, Staff Research Scientist, Google DeepMind, and Bryan Perozzi, Senior Staff Research Scientist, Google Research With the recent and accelerated advances in machine learning (ML), machines can understand natural language, engage in conversations, draw images, create videos and more. Modern ML models are programmed and

Read More
Shared by Google AI Technology December 15, 2023