Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

no code implementations • 29 Mar 2022 • Siyuan Guo, Viktor Tóth, Bernhard Schölkopf, Ferenc Huszár

It is known that under i.\, i.\, d assumption, even with infinite data, there is a limit to how fine-grained a causal structure we can identify.

Causal Inference

Autoencoding sensory substitution

1 code implementation • 14 Jul 2019 • Viktor Tóth, Lauri Parkkonen

To overcome these obstacles, we developed a novel class of SS methods, by training deep recurrent autoencoders for image-to-sound conversion.