TensorFlow is an open source platform for machine learning provided by Google.

Installation tutorial


Built on top of TensorFlow 2, Keras is a central part of the tightly-connected TensorFlow 2 ecosystem, covering every step of the machine learning workflow, from data management to hyperparameter training to deployment solutions.

Keras is used by CERN (e.g., at the LHC), NASA and many more scientific organizations around the world. Furthermore, it is the most used deep learning framework among top-5 winning teams on Kaggle.

Note that Keras offers many code examples with short (less than 300 lines of code), focused demonstrations of deep learning workflows. All of the examples are written as Jupyter notebooks and can be run in one click in Google Colab.

First steps#

Next, we take a look at how to build a deep neural network model using TensorFlow 2 and Keras. The content is based on Laurence Moroney’s excellent Tutorial “Intro to Machine Learning” (see video below):

Google’S AI Advocate Laurence Moroney walks you through the code provided in the presentation: