Learn More

In 2016, Udacity released the very first free course on TensorFlow in collaboration with Google. Since then, over 400,000 students have enrolled in the course and joined the AI revolution. We’re excited to release an all-new version of this free course featuring the just-announced alpha release of TensorFlow 2.0: Intro to TensorFlow for Deep Learning. This update makes AI even more accessible to everyone, and we’ve again worked directly with the deep learning experts at Google to ensure you’re learning the very latest skills to utilize TensorFlow.

Google and Udacity Intro to TensorFlow for Deep Learning course

This free course is a practical approach to deep learning for software developers. Our goal is to get you building state-of-the-art AI applications as fast as possible, without requiring a background in math. If you can code, you can build AI with TensorFlow. You’ll get hands-on experience using TensorFlow to implement state-of-the-art image classifiers and other deep learning models. You’ll also learn how to deploy your models to various environments including browsers, phones, and the cloud.

Machine Learning for Everyone

The alpha release of TensorFlow 2.0 is a big milestone for the product. TensorFlow has matured into an entire end-to-end platform. In this alpha release, TensorFlow has been redesigned with a focus on simplicity, developer productivity, and ease of use. This release integrates Keras more tightly into the rest of the TensorFlow platform so that it’s easier for developers new to machine learning to get started with TensorFlow. Along with standardizing around Keras as the main API, other deprecated and redundant APIs have been removed to reduce complexity in the framework. A general release candidate will be available later in Q2 2019.

Whether you’re just starting out or have years of experience, the alpha release of TensorFlow 2.0 provides easy-to-use APIs so that anyone who knows how to code can build their own AI applications. The new API also provides the flexibility necessary for experimentation and researching new architectures and techniques. Above all, TensorFlow helps you solve challenging, real-world problems with machine learning.

Machine Learning Anywhere

A core strength of TensorFlow has always been the ability to deploy machine learning applications to production anywhere. For phone apps to utilize machine learning well – running as fast as possible, using as little energy as possible – it’s imperative to move your AI system to the devices themselves. Using TensorFlow Lite, your trained models can be deployed to mobile devices such as Android and iOS phones, as well as embedded devices like the Raspberry Pi and autonomous vehicles.

You can also deploy your machine learning models to browsers with TensorFlow.js. In a world of online applications, this framework provides opportunities for innovation beyond what we know today. TensorFlow.js also makes it possible to run machine learning systems in Node.js applications, so you aren’t locked into Python or C++.

For scaling your applications to users around the world, you’ll want to deploy to the cloud using TensorFlow Serving. This system provides an easy way to deploy algorithms and rapidly experiment in a high-performance production environment. It can also be extended to build out an entire data processing and monitoring pipeline for your applications.

Learn TensorFlow With Us

We’re excited to partner with Google’s TensorFlow team to bring you a free 2-month course that will teach any software developer how to build AI applications that scale. We’re releasing the first 3 lessons today, and more will be made available every 3-4 weeks.

In the first part of this course, you’ll learn some of the fundamental concepts behind machine learning, and how to build and train neural networks using TensorFlow. You’ll learn via exercises and Colab notebooks written by the TensorFlow team, where you will explore some of the most common applications of neural networks. You’ll start by learning how to train a neural network to be able to convert Celsius degrees to Fahrenheit degrees. Next, you will learn how to train a deep neural network to be able to recognize articles of clothing in images from the Fashion MNIST dataset.

Then, you’ll learn about Convolutional Neural Networks (CNN), data augmentation, and transfer learning. You’ll learn how to use these techniques to increase the accuracy of deep neural networks and you’ll get hands-on experience by optimizing and testing your neural networks on different image datasets. Later in the course, you’ll learn how to deploy your trained models on browsers, Android, iOS, and embedded devices like the Raspberry Pi, as well as how to perform object detection, and much more.

This free course is part of Udacity’s School of AI, a set of free courses and Nanodegree programs designed by and for software developers. Our catalog covers a huge range of topics such as linear algebra and calculus, foundational machine learning models, and state-of-the-art deep learning. You’ll also be able to gain skills in domains such as computer vision, natural language processing, and deep reinforcement learning.

TensorFlow is helping to power the ML revolution and we’re thrilled to bring it to all of you in collaboration with Google. Starting your journey in the field of AI has never been easier.

Enroll today to get hands-on experience building AI applications taught by deep learning experts.

Enroll Now

Mat Leonard
Mat Leonard
Mat Leonard is Product Lead for Udacity's School of Artificial Intelligence. He is a former physicist, research neuroscientist, and data scientist. He did his PhD and Postdoctoral Fellowship at the University of California, Berkeley.