Deep Learning Course v2.0
Master in Fundamental Principles of Data Science
Jordi Vitrià, Universitat de Barcelona, 2020
[fast_rewind Previous Page](deep2.html) [Next Page fast_forward](deep4.html)
TensorFlow is an open source library for numerical computation and large-scale machine learning. TensorFlow bundles together a slew of machine learning and deep learning (aka neural networking) models and algorithms and makes them useful by way of a common metaphor. It uses Python to provide a convenient front-end API for building applications with the framework, while executing those applications in high-performance C++.
Keras is TensorFlow's high-level API for building and training deep learning models. It's used for fast prototyping, state-of-the-art research, and production. The guide Keras: A Quick Overview will help you get started.
Keras and TensorFlow 2.0 provide you with three methods to implement your own neural network architectures:
- Sequential API
- Functional API
- Model subclassing
Inside of this tutorial you’ll learn how to utilize each of these methods, including how to choose the right API for the job.
!!! Note Keras for Engineers Are you a machine learning looking to use Keras to ship deep-learning powered features in real products? This guide will serve as your first introduction to core Keras API concepts. Colab Notebook open_in_new
!!! Note Keras for Researchers Are you a machine learning researcher? Do you publish at NeurIPS and push the state-of-the-art in CV and NLP? This guide will serve as your first introduction to core Keras API concepts. Colab Notebook open_in_new
[fast_rewind Previous Page](deep1.html) [Next Page fast_forward](deep3.html)