Communications of the ACM
Algorithms May Lead to More Robust Machine Learning Applications
Credit: Center for Imaging Science
Scientists are looking to develop robust algorithms that can provide more efficient machine learning applications by focusing on concepts that lie at the intersection of algebra and geometry.
Hariharan Narayanan, assistant professor at Tata Institute of Fundamental Research Mumbai, and a recipient of the Swarna Jayanti fellowship, wishes to create machine learning algorithms that can learn from observations and make improved predictions based on mathematical objects known as manifolds and Lie groups. This can lead to improved modelling of data arising from certain sources, such as visual observations.
The use of manifolds and Lie groups may lead to algorithms that make better predictions in real-life applications.
From Devdiscourse
View Full Article
No entries found