Congratulations on completing the Big Data and Machine Learning Fundamentals course! We hope that you learned some valuable information from this course that will help advance your career. Throughout the course, we introduced a number of products and technologies to support Google’s data-to-AI lifecycle. Let’s do a final review of the main concepts presented. In the first section of the course, you were introduced to the Google Cloud infrastructure and Google’s big data and machine learning products. Of the three layers of the Google Cloud infrastructure, you explored the middle and top layers. On the middle layer sit compute and storage. Google Cloud decouples compute and storage so they can scale independently based on need. And on the top layer sit the big data and machine learning products, which enable you to perform tasks to ingest, store, process, and deliver business insights, data pipelines, and machine learning models. In the second section of the course, you explored data engineering for streaming data. This included how to build a streaming data pipeline– from ingestion with Pub/Sub, to processing with Dataflow, to visualization using Data Studio and Looker. After that, in the third section of the course, you were introduced to BigQuery, which is Google’s fully-managed data warehouse. BigQuery provides two services in one: storage plus analytics. You also learned about BigQuery ML, the machine learning tool used for developing machine learning models directly in BigQuery. In the fourth section of the course, you explored the options available to build and deploy machine learning models with Google Cloud. If you’re familiar with SQL and already have data in BigQuery, you can use BigQuery ML to develop machine learning models. If you have little ML experience, using pre-built APIs is likely the best choice. Pre-built APIs address common perceptual tasks such as vision, video, and natural language. They’re ready to use without any ML expertise or model development effort. If you want to build custom models with your own training data while spending minimal time coding, then AutoML is a great choice. AutoML provides a code-less solution to enable you to focus on business problems instead of the underlying model architecture and ML provisioning. And if you want full control of the machine learning workflow, Vertex AI custom training lets you train and serve custom models with code on Vertex Workbench. Using pre-built containers, you can leverage popular ML libraries, such as Tensorflow and PyTorch. Alternatively, you can build a custom container from scratch. In the final section of the course, you learned about the machine learning workflow using Vertex AI, a unified platform that brings all the components of the machine learning ecosystem and workflow together. The machine learning workflow comprises three stages. In stage one, data preparation, data is uploaded and feature engineering is applied. In stage two, model training, the model is trained and evaluated. And in stage three, model serving, the model is deployed and monitored. We hope that this course is just the beginning of your big data and machine learning journey. For more training and hands-on practice with data engineering and analytics, please refer to cloud.google.com/training/data-engineering-and-analytics. And for more training with machine learning and AI, please explore the options available at cloud.google.com/training/machinelearning-ai. And if you’re interested in validating your expertise and showcasing your ability to transform businesses with Google Cloud technology, you might consider working toward a a Google Cloud certification. You can learn more about Google Cloud’s certification offerings at cloud.google.com/certifications. Thanks for completing this course. We’ll see you next time!
