Andrew Y. Ng

TL;DR: In this article, the authors used a BERT model to directly map from a radiology report to the image labels, with a supervisory signal determined by a computer vision model trained to detect medical conditions from chest X-ray images.

TL;DR: It is shown that the inclusion of Möbius transformations during training enables improved generalization over prior sample-level data augmentation techniques such as cutout and standard crop-and-flip transformations, most notably in low data regimes.

TL;DR: This work presents a method for quantifying disentanglement that only uses the generative model, by measuring the topological similarity of conditional submanifolds in the learned representation and finds that this method ranks models similarly to existing methods.

TL;DR: A morphologic analysis of histology sections from 209 DLBCL cases with associated clinical and cytogenetic data suggests that geometric features computed from tumor nuclei are of prognostic importance, and should be validated in prospective studies.

TL;DR: Many robotic control problems, such as autonomous helicopter flight, legged robot locomotion, and autonomous driving, remain challenging even for modern reinforcement learning algorithms, but when allowed to learn from a human demonstration of a task, a number of efficient algorithms can be used to address each of these problems.