We recently built the Berkeley Crossword Solver (BCS), the first computer program to beat every human competitor in the world’s top crossword tournament.
The expressivity of current deep probabilistic models can be improved by selectively prioritizing statistical dependencies between latent variables that are potentially distant from each other.
How we depict the state of technology (imagined, current or future) visually and verbally, helps us position ourselves in relation to what is already there and what is coming.
In this blog post, we aim to understand if, when and why offline RL is a better approach for tackling a variety of sequential decision-making problems.
A computational tool developed to predict the structure of protein complexes is providing new insights into the biomolecular mechanisms of their function.
To better understand advances in AI as a part of the education of health sciences students, researchers conducted a comprehensive literature review and hosted a virtual panel.