Philosophy of Physics Seminar (Thursday - Week 1, TT22)

Philosophy of Physics

In algorithmic information theory (AIT), Levin's coding theorem (which should be much more widely taught in Physics!)  predicts that, upon uniform random sampling of programmes, a universal Turing machine (UTM) will be exponentially biased towards outputs with low Kolmogorov complexity. In this talk I will provide evidence for a similar exponential  bias towards descriptional simplicity (low Kolmogorov complexity) in biological evolution. A similar Occam's razor-like bias helps explain why deep neural networks generalize well in the overparameterised regime, where classical learning theory predicts they should badly overfit.   I will discuss how these principles from AIT fit into a wider discussion about the use (and abuse) of Occam's razor in science. 

Philosophy of Physics Seminar Convenor for TT22: Simon Saunders  | Philosophy of Physics Group Website