3

For a recently introduced class of autoencoders, we prove that they orient the encoding level sets exactly with respect to the data distribution, and if the latter lies on a lower-dimensional manifold, the extra encoding dimensions carry absolutely no additional information. The former leads to a remarkable performance in cases where the data comes from a physical simulation, where the method can recover the minimum free energy path, while the latter opens up possibilities of testing for manifold dimensionality, for example.

In the paper, we combine approaches that help discover how known properties of human language are learned by generative models when trained on labeled speech audio data with methodology inspired by causal inference and apply it to the communication system of sperm whales, for which we do not have any such ground truth. With this, we can propose what components of their communication might serve as the carriers of meaning, not only giving credence to existing theories but also suggesting additional ways the whales might encode information.

Translation Quality Assessment (TQA) is a process conducted by human translators and is widely used, both for estimating the …