175 citations · 1.1k across the 47 of their papers we have counts for
3 papers · 1 filter
Cellular automata can classify data by inducing trajectory phase coexistence
Stephen Whitelam, Isaac Tamblyn
We show that cellular automata can classify data by inducing a form of dynamical phase coexistence. We use Monte Carlo methods to search for general two-dimensional deterministic a…
Correspondence between neuroevolution and gradient descent
Stephen Whitelam, Viktor Selin, Sang-Won Park +1
We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient…
Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning
Chris Beeler, Uladzimir Yahorau, Rory Coles +3
Using a model heat engine, we show that neural network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gra…