In a recent paper, SFI Complexity Postdoctoral Fellow Yuanzhao Zhang and co-author William Gilpin show that a deceptively ...
Working with non-numerical data can be tough, even for experienced data scientists. A typical machine learning model expects its features to be numbers, not words, emails, website pages, lists, graphs ...
Machine learning has moved past its initial experimental phase. In earlier years, development often focused on creating the largest possible models to see what capabilities might appear. Today, the ...
Machine learning can sound pretty complicated, right? Like something only super-smart tech people get. But honestly, it’s ...
The creative new approach could lead to more energy-efficient machine-learning hardware. On a table in his lab at the University of Pennsylvania, physicist Sam Dillavou has connected an array of ...
A research team of mathematicians and computer scientists has used machine learning to reveal new mathematical structure within the theory of finite groups. By training neural networks to recognise ...