DIEP seminar by Ard Louis
The coding theorem from algorithmic information theory (AIT) - which should be much more widely taught in science- suggests that many processes in nature are highly biased towards highly compressible outputs with lower Kolmogorov complexity. Ard Louis will explore applications to biological evolution, where the coding theorem implies an exponential bias towards outcomes with higher symmetry [1], and to machine learning, where the coding theorem predicts an Occam's razor like bias that helps explain why deep neural networks generalise so well even though they are overparameterized [2].
[1] Symmetry and simplicity spontaneously emerge from the algorithmic nature of evolution
Iain G Johnston et al, PNAS 119, e2113883119 (2022).
[2] Deep neural networks have an inbuilt Occam’s Razor, C. Mingard et al, Nat Comm.16, 220 (2025)
Ard Louis is a theoretical physicist with a broad interdisciplinary set of interests, including self-assembling DNA, theories of evolution, the dynamics of soft matter, machine learning and applications of algorithmic information theory. He happily collaborates with biologists, chemists, computer scientists, mathematicians, philosophers and theologians. After his first degree in physics from the University of Utrecht, he completed a PhD with Neil Ashcroft at Cornell. He was a Royal Society Research Fellow in Theoretical Chemistry at the University of Cambridge, before moving to the Rudolf Peierls Centre for Theoretical Physics at the University of Oxford His Erdős–Bacon number is 6 through Jonathan Doye and Morgan Freeman.
If you wish to attend this seminar online, please send an email to r.lier@uva.nl to receive the zoom-link.