Hopfield models of associative memory.Oberseminar Mathematics of Artificial Intelligence

by Véronique Gayrard

Monday Jul 20, 2026, 12:45 PM → 2:00 PM Europe/Berlin

Seminar Room 1.008 (Endenicher Allee 60)

In 1982, condensed matter physicist John Hopfield drew inspiration from the physics of spin glasses in order to devise simple artificial neural networks that could learn and remember. This not only revived the largely abandoned field of neural networks, but also built bridges between the fields of statistical mechanics, computational neuroscience and machine learning. His pioneering work was recognised with the award of the 2024 Nobel Prize in Physics.
In this talk, I will first introduce these models and present a non-technical overview of the most significant known results, covering predictions from theoretical physics and mathematically rigorous results. In the second part, I will discuss recent mathematical progress in understanding how false memories are formed alongside intended memories during the learning process.