My name is Gwendolyn Stripling and I am the Technical Curriculum Developer for Machine Learning here at Google Cloud. Welcome to our specialization Machine Learning on Google Cloud. So what is machine learning and what kinds of problems can it solve? Why are neural networks so popular today? What are some of Google's pre-trained machine learning models? How can you design and build a machine learning model using Tensorflow 2.9x and Keras? Finally, how do you train models at scale with Cloud AI platform? You will learn this and more in this specialization. Our machine learning on Google Cloud Specialization is a practical real-world introduction to Machine Learning. Let's take a closer look at our course offerings. We begin the specialization with this course, how Google does Machine Learning. We introduced Machine Learning and what we mean when we say we are a AI first, we then introduce you to Google's pre-trained ML APIs, such as vision, speech to text, and Dialogflow. We then discuss how to transform your business with machine learning and how Google does machine learning. We introduce you to inclusive ML, where we'd look at biased in machine learning. Lastly, we show you how you can get started very quickly building a machine learning model with Cloud AI platform Jupyter Notebooks. Launching into machine learning begins with a discussion about data, how to improve data quality and perform exploratory data analysis. We then discuss how to set up a supervised learning problem, how to optimize a machine learning model, and how generalization and sampling can help assess the quality of ML models. We then move on to Introduction to TensorFlow 2.x. This course shows you how to design and build a TensorFlow 2.x input data pipeline. Use the tf.data library to manipulate data and large data-sets and use the Keras sequential and functional APIs for simple and advanced model creation. Also, you'll learn how to train, deploy, and productionalize ML models at scale using Cloud AI Platform. Feature engineering is often the longest and most difficult phase of building a machine learning project. Think of this section as filling your tool chest with a set of ideas to help you improve model accuracy. You will use different ideas and different situations. So you will find that knowing them will be helpful in your career as you solve different ML problems. We end the specialization with the art and science of machine learning. In this course, you learned the essential skills of ML intuition, good judgment, and experimentation to finally tune and optimize your ML models for the best performance. You will learn about hyperparameters, the mini knobs and levers involved in training a model. Once familiar with hyperparameters, you will learn how to tune them in an automatic way using Cloud AI platform notebooks on Google Cloud. Let's get started.