Machine Learning on Google Cloud

Paths

Machine Learning on Google Cloud

Author: Google Cloud

This path teaches course participants how to write distributed machine learning models that scale in TensorFlow, scale out the training of those models, and offer high-performance... Read more

What you will learn:

This path teaches the following skills

  • Think strategically and analytically about machine learning as a business process and consider ML’s fairness implications with respect to ML
  • Understand how ML optimization works and how various hyperparameters affect models during optimization
  • Write models in TensorFlow using both pre-made estimators and custom estimators
  • Train rain them locally or in Cloud AI Platform
  • Understand why feature engineering is critical to success
  • Use essential skills of ML intuition, good judgment and experimentation to finely tune and optimize your ML models for the best performance.
  • How to do hyperparameter tuning with Cloud AI Platform

Pre-requisites

Participants should have a basic understanding of querying with SQL and programming in Python.

Beginner

This section builds upon the previous course in the path. Google thinks about machine learning as being about logic, rather than just data. You will learn why such a framing is useful for data scientists when thinking about building a pipeline of machine learning models. You will learn about the five phases of converting a candidate use case to be driven by machine learning, and why it is important the phases not be skipped. You will examine how machine learning can amplify bias. Next you will examine why neural networks today perform so well in a variety of data science problems. You will then learn to set up a supervised learning problem and find a good solution using gradient descent. To do so, you must ensure that your datasets permit generalization; the course covers methods of doing so in a repeatable way that supports experimentation.

How Google Does Machine Learning

by Google Cloud

Aug 3, 2019 / 3h 20m

3h 20m

Start Course
Description

What is machine learning, and what kinds of problems can it solve? Google thinks about machine learning slightly differently -- of being about logic, rather than just data. We talk about why such a framing is useful when thinking about building a pipeline of machine learning models. Then, we discuss the five phases of converting a candidate use case to be driven by machine learning, and consider why it is important the phases not be skipped. We end with a recognition of the biases that machine learning can amplify and how to recognize this.

Table of contents
  1. Introduction to Specialization
  2. What It Means to Be AI First
  3. How Google Does ML
  4. Inclusive ML
  5. Python Notebooks in the Cloud
  6. Summary

Launching into Machine Learning

by Google Cloud

Aug 3, 2019 / 3h 19m

3h 19m

Start Course
Description

Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way so as to support experimentation.

Table of contents
  1. Introduction
  2. Practical ML
  3. Optimization
  4. Generalization and Sampling
  5. Summary

Intermediate

In this section you work with low-level TensorFlow, progressing through the necessary concepts and APIs so as to be able to write distributed machine learning models. You will learn, given a TensorFlow model, how to scale out the training of that model and offer high-performance predictions using Cloud Machine Learning Engine. You will learn how to perform feature engineering, including recognizing the elements of good versus bad features, and how you can preprocess and transform them for optimal use in your machine learning models. You will get hands-on practice choosing features and preprocessing them inside of Google Cloud Platform with interactive labs.

Introduction to TensorFlow

by Google Cloud

Aug 3, 2019 / 3h 0m

3h 0m

Start Course
Description

In this course, you will learn how to create machine learning models in TensorFlow which is the tool we will use to write machine learning programs. You’ll learn how to use the TensorFlow libraries to solve numerical problems. When writing programs, you often want to know about common mistakes that you might run into, and how to fix common errors. Then, we’ll look at the Estimator API, which provides the highest level abstraction within TensorFlow for training, evaluating and serving machine learning models. You will learn how to Use tf_estimator to create, train, and evaluate an ML model. Finally, you’ll learn how to execute TensorFlow models on Cloud AI Platform, Google-managed infrastructure to run TensorFlow. You will learn how to Train, deploy, and productionalize ML models at scale with Cloud AI Platform.

Table of contents
  1. Introduction
  2. Core TensorFlow
  3. Estimator API
  4. Scaling TensorFlow models with Cloud AI Platform
  5. Summary

Feature Engineering

by Google Cloud

Aug 3, 2019 / 4h 7m

4h 7m

Start Course
Description

Want to know how you can improve the accuracy of your ML models? What about how to find which data columns make the most useful features? Welcome to Feature Engineering where we will discuss good vs. bad features and how you can preprocess and transform them for optimal use in your models.

Table of contents
  1. Introduction
  2. Raw data to features
  3. Preprocessing and feature creation
  4. Feature crosses
  5. TensorFlow Transform
  6. Summary

Advanced

In this section, you will first learn about aspects of machine learning that require some intuition, good judgment, and experimentation. We call it the art of ML. We will learn the many knobs and levers involved in training a model. You will manually adjust them to see their effects on model performance. Once familiar with the knobs and levers, otherwise known as hyper parameters, you will learn how to tune them in an automatic way using Cloud AI Platform on Google Cloud Platform. You'll further spice things up by pinch of science, and the science involved in training neural networks. You will also learn the important concept of embeddings which is all about representing discrete objects such as words as real valued vectors. Finally, you will switch from working with TensorFlow's pre-built estimators such as DNN Regressor to building your own custom estimators

The Art and Science of ML

by Google Cloud

Aug 3, 2019 / 3h 30m

3h 30m

Start Course
Description

Welcome to the art and science of machine learning. In this data science course you will learn the essential skills of ML intuition, good judgment and experimentation to finely tune and optimize your ML models for the best performance.

In this course you will learn the many knobs and levers involved in training a model. You will first manually adjust them to see their effects on model performance. Once familiar with the knobs and levers, otherwise known as hyperparameters, you will learn how to tune them in an automatic way using Cloud Machine Learning Engine on Google Cloud Platform.

Table of contents
  1. Introduction
  2. The Art of ML
  3. Hyperparameter Tuning
  4. A Pinch of Science
  5. The Science of Neural Networks
  6. Embeddings
  7. Custom Estimator
  8. Summary