Machine learning is a hot topic these days and Google has been one of the biggest newsmakers. Google’s machine learning is being used behind the scenes every day by millions of people. When you search for an image on the web or use Google Translate on foreign language text or use voice dictation on your Android phone, you’re using machine learning. Now Google has launched AI Platform to give its customers the power to train their own neural networks.
This is a hands-on course where you can follow along with the demos using your own Google Cloud account or a trial account.
- Describe how an artificial neural network functions
- Run a simple TensorFlow program
- Train a model using a distributed cluster on AI Platform
- Increase prediction accuracy using feature engineering and hyperparameter tuning
- Deploy a trained model on AI Platform to make predictions with new data
- The GitHub repository for this course is at https://github.com/cloudacademy/aiplatform-intro.
- December 20, 2020: Completely revamped the course due to Google AI Platform replacing Cloud ML Engine and the release of TensorFlow 2.
- Nov. 16, 2018: Updated 90% of the lessons due to major changes in TensorFlow and Google Cloud ML Engine. All of the demos and code walkthroughs were completely redone.
Welcome to “Introduction to Google AI Platform”. My name’s Guy Hummel and I’m a Google Certified Professional Machine Learning Engineer. If you have any questions, feel free to connect with me on LinkedIn and send me a message, or send an email to firstname.lastname@example.org.
This course is intended for anyone who’s interested in machine learning. I’ll be showing you how to build and run neural networks on the Google Cloud Platform.
To get the most from this course, you should have some experience writing Python code. You don’t need to have prior experience with machine learning, though, because we’ll go over the basics at the beginning of this course. I recommend that you have a Google Cloud Platform account so you can follow along with the examples in this course and do them yourself. If you don’t already have one, then you can create a free trial account.
To save you the trouble of typing in the URLs shown in this course, I’ve created a GitHub repository with a readme file that contains all of the URLs. The link to the repository is at the bottom of the course overview below.
To train your first neural network, we’ll start by going over machine learning concepts. Then, we’ll go through a TensorFlow program and run it. TensorFlow is a set of Python libraries that make it easier to create neural networks. Google open sourced it in 2015.
Next, you’ll learn about deep neural networks and then use Google AI Platform to train your machine learning model.
To see how to improve the accuracy of models, we’ll use feature engineering and then explain hyperparameter tuning.
After that, we’ll scale up by training a model using a distributed cluster on AI Platform and then deploy the trained model, so we can use it to make predictions.
We’d love to get your feedback on this course, so please give it a rating when you’re finished.
Now, if you’re ready to learn how to train a machine learning model on the Google Cloud Platform, then let’s get started.
Guy launched his first training website in 1995 and he's been helping people learn IT technologies ever since. He has been a sysadmin, instructor, sales engineer, IT manager, and entrepreneur. In his most recent venture, he founded and led a cloud-based training infrastructure company that provided virtual labs for some of the largest software vendors in the world. Guy’s passion is making complex technology easy to understand. His activities outside of work have included riding an elephant and skydiving (although not at the same time).