fb pixel

Dr. James Halverson Colloquium

Fri. Oct. 22 12:30 PM - Fri. Oct. 22 01:20 PM
Contact: Andrea Wiebe
Location: via Zoom

Dr. James Halverson

Associate Professor, Dept of Physics, Northeastern University


Build Quantum Fields out of Neurons

Deep learning is everywhere, powered by neural networks. When a neural network is born, it's a random function, but so, too, are quantum fields, and in recent years ideas from quantum field theory have influenced machine learning. In this colloquium I will push the influence the other direction, developing an approach to quantum field theory in which fields inherit their intrinsic randomness from N constituent random neurons. Some setups yield reflection positive and Euclidean-invariant ensembles, allowing for analytic continuation to a Lorentz-invariant quantum field theory. Near-Gaussianity is exhibited at large-N, potentially explaining a feature of field theories in Nature.


BIO: Jim Halverson is an Associate Professor of Physics at Northeastern University in Boston, Massachusetts.

His research is at some of the interfaces between string theory, particle physics, cosmology, mathematics, and deep learning. He is particularly interested in the string landscape and its implications for particle physics and cosmology beyond their standard models. These implications often follow from the structure of extra-dimensional geometries, of which there are many possibilities. Halverson’s research therefore requires importing techniques from mathematics and computer science.

Recently, Halverson’s interest in the interface of physics and deep learning has continued to grow. To that end, he is a co-PI and serves on the institute board of the NSF AI Institute for Artificial Intelligence and Fundamental Interactions (IAIFI) and co-organizes Physics ∩ ML.


For a zoom invitation to this event, please contact Andrea Wiebe at an.wiebe@uwinnipeg.ca.