Tag Archives: james sethian ms d method

Berkeley Lab ‘Minimalist Machine Learning’ Algorithms Analyze Images From Very Little Data

CAMERA researchers develop highly efficient convolution neural networks tailored for analyzing experimental scientific images from limited training data

Mathematicians at the Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab) have developed a new approach to machine learning aimed at experimental imaging data. Rather than relying on the tens or hundreds of thousands of images used by typical machine learning methods, this new approach “learns” much more quickly and requires far fewer images. (more…)

Read More

UCL professors use probabilities to persuade doubters skeleton is King Richard III

Two UCL professors led a key part of the new analysis of ‘Skeleton 1’; which was discovered in a Leicester car park in 2012 on the site of the Grey Friars friary, the last known resting place of King Richard III. They used probability calculations to combine several different lines of evidence, producing an overall weight-of-evidence for the skeleton being that of King Richard III. Their work forms part of a research study led by Dr Turi King at the University of Leicester and published in Nature Communications. (more…)

Read More