Zakaria Haque

TL;DR: Wide & Deep learning is presented---jointly trained wide linear models and deep neural networks---to combine the benefits of memorization and generalization for recommender systems and is open-sourced in TensorFlow.

TL;DR: Wide & Deep as mentioned in this paper combines the benefits of memorization and generalization for recommender systems by jointly trained wide linear models and deep neural networks, which can generalize better to unseen feature combinations through lowdimensional dense embeddings learned for the sparse features.

TL;DR: TensorFlow Extended (TFX) is presented, a TensorFlow-based general-purpose machine learning platform implemented at Google that was able to standardize the components, simplify the platform configuration, and reduce the time to production from the order of months to weeks, while providing platform stability that minimizes disruptions.

TL;DR: In this article, the authors present a framework for specifying, training, evaluating, and deploying machine learning models, which allows users to write code to define their models, but provides abstractions that guide developers to write models in ways conducive to productionization.

TL;DR: To make out of the box models flexible and usable across a wide range of problems, these canned Estimators are parameterized not only over traditional hyperparameters, but also using feature columns, a declarative specification describing how to interpret input data.