Learn with Google AI

This document is intended to help those with a basic knowledge of machine learning get the benefit of Google's best practices in the field. It presents a style for machine learning, similar to the Google C++ Style Guide and other popular guides to practical programming. If you have taken a class in machine learning, or worked on a machine­-learned model, then you have the necessary background to read this document.

Machine learning is one of the fastest-growing and most exciting fields out there, and deep learning represents its true bleeding edge. In this course, you’ll develop a clear understanding of the motivation for deep learning, and design intelligent systems that learn from complex and/or large-scale datasets.

In this lab, you will learn how to create a Vision API request and how to call the API with curl. You will then send images to the Vision API and see it detect objects, faces, and landmarks.

In this lab, you go from exploring a taxicab dataset to training and deploying a high-accuracy distributed model with Cloud ML Engine.

In this lab, you will go through the process of building a complete machine learning pipeline covering ingest, exploration, training, evaluation, deployment, and prediction.

This free, online course is for someone who wants to start doing data science and machine learning right now. You’ll spend more time writing code than reading about it. You’ll get the theoretical background you need to make good modeling decisions, but won’t waste your time with historical background that won’t help you become a practicing data scientist.

Challenge yourself with real-world focused machine learning competitions, complete with extensive tutorials to help you succeed. Build a model to make predictions and upload your submission file to see your score on a live leaderboard.

This five-course accelerated specialization is designed for data professionals who are responsible for designing, building, analyzing, and optimizing big data solutions. Through a combination of video lectures, quizzes, and hands-on labs, you'll learn how to carry out serverless data analysis and productionize machine learning models. This specialization is designed to give participants a robust hands-on experience and is primarily lab-focused.

In this codelab, you're going to take an existing Android app and add a TensorFlow model to generate stylised images using the device's camera. You can also use the techniques outlined in this codelab to implement any TensorFlow network you have already trained.

In this codelab, you will learn how to train a custom image recognition model on a pre-made Android app. The outcome is a simple camera app that runs a TensorFlow image recognition program to identify flowers.

In this codelab, you will learn how to run TensorFlow on a single machine, and will train a simple classifier to classify images of flowers.