Skip to main content
Browse by:
GROUP

Effective March 10, 2020, all Duke-sponsored events over 50 people have been cancelled, rescheduled, postponed or virtualized.
Please check with the event contact regarding event status. For more information, please see https://coronavirus.duke.edu/events

Stochastic Thermodynamics of Learning

Event Image
Icon calendar
Thursday, April 26, 2018
Icon time
1:00 pm - 2:30 pm
Icon speaker
Sebastian Goldt
Icon series
Computational Neuroscience Meeting

Unravelling the physical limits of information processing is an important goal of non-equilibrium statistical physics. It is motivated by the search for fundamental limits of computation, such as Landauer's bound on the minimal work required to erase one bit of information. Further inspiration comes from biology, where we would like to understand what makes single cells or the human brain so (energy-)efficient at processing information.

In this talk, we analyse the thermodynamic efficiency of learning. We first discuss the interplay of information processing and dissipation from the perspective of stochastic thermodynamics. We then show that the dissipation of any physical system, e.g. a neural network, bounds the information that it can infer from data or learn from a teacher. We discuss a number of examples along the way and outline directions for future research.