The 2025 Martin Lecture featuring Geoffrey Hinton — Boltzmann Machines

Recorded February 25, 2025. In his talk “Boltzmann Machines: Statistical Physics meets Neural Networks,” 2024 Nobel Laureate Geoffrey Hinton explores his invention of the Boltzmann machine, an early example of an unsupervised deep learning model. Hinton’s work has helped lead to advancements in a wide range of areas, such as speech recognition and object classification, that greatly impact our lives today. Hinton was awarded the 2024 Nobel Prize in Physics for his revolutionary work enabling machine learning with artificial neural networks. A University Professor Emeritus of computer science at the University of Toronto, Hinton is internationally renowned as a pioneer in the field of deep learning as a mode of artificial intelligence. His many accolades include the Companion of the Order of Canada (2019). The Martin Lecture series is held annually, welcoming top thinkers and researchers in Astronomy & Astrophysics, Ecology & Evolutionary Biology, Physics, and Public Policy to the University of Toronto.