Anima Anandkumar is Bren Professor of Computing at the California Institute of Technology and senior director of Machine Learning Research at Nvidia.
Anima Anandkumar has a bone to pick with the matrix. Her misgivings are not about the sci-fi movies, but about mathematical matrices—grids of numbers or variables used throughout computer science. While researchers typically use matrices to study the relationships and patterns hiding within large sets of data, these tools are best suited for two-way relationships. Complicated processes such as social dynamics, on the other hand, involve higher-order interactions.
"In practice, matrix methods in machine learning can't effectively capture higher-order relationships," Anandkumar says in an interview. "Essentially, you can't learn at all. So we asked: What if we looked at higher-order [operations]? That got us into tensor algebra."
From Quanta Magazine
View Full Article