Causal discovery is at the core of human cognition. It enables us to reason
about the environment and make counterfactual predictions about unseen
scenarios, that can vastly differ from our previous experiences. We consider
the task of causal...
Branched flow of light is experimentally observed inside a thin soap membrane, where smooth variations of the membrane thickness transform the light beam into branched filaments of enhanced intensity that keep dividing as the waves propagate.
Automating molecular design using deep reinforcement learning (RL) holds the
promise of accelerating the discovery of new chemical compounds. A limitation
of existing approaches is that they work with molecular graphs and thus ignore
the location of...
New light particles produced in supernovae can lead to additional energy
loss, and a consequent deficit in neutrino production in conflict with the
neutrinos observed from Supernova 1987A (SN1987A). Contrary to the majority of
I just got (and answered) an email from a pair of high school students who are working on using ML techniques for symbolic integration and wanted my opinion on directions they could go in. In passing...
We present a novel nonparametric algorithm for symmetry-based disentangling
of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER).
GEOMANCER provides a partial answer to the question posed by Higgins et al.
(2018): is it possible...