TensorFlow has emerged as one of the most popular deep learning frameworks in use today. It has by far more users and contributors than any other project, and appears to be continuing on its upward trajectory with the release of the TensorFlow 2.0 API. There are many new features of the TensorFlow 2.0 API to look through, and we will discuss many of them, including eager execution, notebook accessible tensorboards, and tighter integration with Keras. In addition, we will show how edge calculations can be accelerated with tensorflow.js which runs completely in the browser and provides much faster model serving. TensorFlow Lite is a framework for running on smaller remote devices. We will also discuss the parallel execution framework, as TensorFlow is well on the way to becoming the standard for all things deep learning.
Jerome Nilmeier is a developer advocate, data scientist, and member of the IBM Center for Open source Data and AI Technologies (CODAIT), where he works with with open source frameworks for big data, machine learning, and deep learning as a developer advocate. He has recently published an O'Reilly Manual, "Data Science and Engineering at Enterprise Scale", which is a great introductory text for data scientists interested in machine learning, big data, and AI.
He has a BS in Chemical Engineering from UC Berkeley, a PhD in Computational Biophysics from UC San Francisco, and has carried out postdoctoral research in biophysics and bioinformatics at UC Berkeley, Lawrence Berkeley and Livermore Laboratories, and at Stanford as an OpenMM Fellow. Just prior to joining IBM, he completed the Insight Data Engineering program in late 2014. He has been with IBM since 2015.