Andrew Y. Ng

TL;DR: This paper presents a new algorithm for automatically learning hypernym (is-a) relations from text, using "dependency path" features extracted from parse trees and introduces a general-purpose formalization and generalization of these patterns.

TL;DR: In this paper, a 9-layered locally connected sparse autoencoder with pooling and local contrast normalization was used to learn high-level, class-specific feature detectors from only unlabeled data.

TL;DR: CheXpert as discussed by the authors is a large dataset of chest radiographs of 65,240 patients annotated by 3 board-certified radiologists with 14 observations in radiology reports, capturing uncertainties inherent in radiograph interpretation and different approaches to using the uncertainty labels for training convolutional neural networks that output the probability of these observations given the available frontal and lateral radiographs.

TL;DR: It is shown that when represented in the information form, map posteriors are dominated by a small number of links that tie together nearby features in the map, which is developed into a sparse variant of the EIF, called the sparse extended information filter (SEIF).

TL;DR: It is argued that modern graphics processors far surpass the computational capabilities of multicore CPUs, and have the potential to revolutionize the applicability of deep unsupervised learning methods.