Did you know that you can convert a Keras model to a TensorFlow Estimator? It will give you a whole host of options around distributed training and scaling. We’re going to prepare a Keras model for running at scale by converting it to a TensorFlow estimator. Keras model, meet Estimator So we have…

This is a short post — the real substance is in the screencast below, where I walk through the code! If you’re getting started in the machine learning world (and let’s be real here, who isn’t?), the tooling seems to just keep getting better and better. Keras has been a…

Scikit-learn is great for putting together a quick model to test out your dataset. But what if you want to run it against incoming live data? Find out how to serve your scikit-learn model in an auto-scaling, serverless environment!

Scikit-learn has long been a popular library for getting started with machine learning. However, not everyone has had a chance to try it out yet. I’ll show you how to get going on scikit-learn with the shortest path possible, all you need a web browser! In this post…

One of the top things that I get asked about when I give talks is Google Cloud AutoML. Let’s use AutoML Vision alpha to build and deploy a machine learning model that recognizes different types of chairs, along with a few other items sprinkled in for good measure. …

On this episode of AI Adventures, I’ve asked Megan Risdal, Product Lead of Kaggle Datasets, to give us a tour of some of the latest features of Kaggle Kernels and Kaggle Datasets, and to showcase some of the ways to collaborate on Kaggle Kernels. You can catch the video of…

The only thing better than data is big data! But getting your hands on large datasets is no easy feat. From unwieldy storage options to difficulty getting analytics tools to run over the dataset properly, large datasets can lead to all sorts of struggles when it comes to actually doing…

A team at Google set out to make the game of pictionary more interesting, and ended up with the world’s largest doodling dataset, and a powerful machine learning model to boot. How did they do it? What is Quick Draw? “Quick, Draw!” was a game that was initially featured at Google I/O in…

Data is messy. It’s often unbalanced, mislabeled, and sprinkled with wacky values to throw off your analysis and machine learning training. The first step to getting your dataset cleaned up is understanding where it needs cleaning. Today, I’ve got just the tool for the job. Visualize your Data Understanding your data is…