Skip to main content

The latest research from Google

AutoBNN: Probabilistic time series forecasting with compositional bayesian neural networks

Time series problems are ubiquitous, from forecasting weather and traffic patterns to understanding economic trends. Bayesian approaches start with an assumption about the data's patterns (prior probability), collecting evidence (e.g., new time series data), and continuously updating that assumption to form a posterior probability distribution. Traditional Bayesian approaches like Gaussian processes (GPs) and Structural Time Series are extensively used for modeling time series data, e.g., the commonly used Mauna Loa CO2 dataset. However, they often rely on domain experts to painstakingly select appropriate model components and may be computationally expensive. Alternatives such as neural networks lack interpretability, making it difficult to understand how they generate forecasts, and don't produce reliable confidence intervals.

Computer-aided diagnosis for lung cancer screening

Using AI to expand global access to reliable flood forecasts

ScreenAI: A visual language model for UI and visually-situated language understanding

SCIN: A new resource for representative dermatology images

MELON: Reconstructing 3D objects from images with unknown poses

HEAL: A framework for health equity assessment of machine learning performance

Cappy: Outperforming and boosting large multi-task language models with a small scorer

Talk like a graph: Encoding graphs for large language models

Chain-of-table: Evolving tables in the reasoning chain for table understanding

Health-specific embedding tools for dermatology and pathology