Jeffrey Dean

TL;DR: In this paper, the authors proposed a representation of patients' entire, raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format and demonstrated that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization.

TL;DR: The authors propose to add an artificial token at the beginning of the input sentence to specify the required target language, which improves the translation quality of all involved language pairs, even while keeping the total number of model parameters constant.

TL;DR: A simple method for constructing an image embedding system from any existing image classifier and a semantic word embedding model, which contains the $ $ class labels in its vocabulary is proposed, which outperforms state of the art methods on the ImageNet zero-shot learning task.

TL;DR: In this article, the authors present a method for placing targeted ads on page on the web (or some other document of any media type) by obtaining content that includes available spots for ads, determining ads relevant to content, and/or combining content with ads determined to be relevant to the content.

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.