O'Reilly logo
live online training icon Live Online training

Democratizing Machine Learning: A Dive into Google Cloud Machine Learning APIs

Romin Irani

Google has been a leader in Machine Learning. In the last few years, it has established itself as both a provider of platforms, frameworks and APIs that help bring Machine Learning to mainstream developers. It provides a complete spectrum of Machine Learning Services that you can use, depending on your comfort level with Machine Learning i.e. as a researcher building your own models, to hosting them and finally as a provider of REST APIs that bring powerful machine learning models within reach of developers.

This training is about the Machine Learning APIs, a set of RESTful interfaces that bring powerful machine learning features to your applications.

This training will give an overview of each of the Machine Learning APIs, along with easy to understand samples that demonstrate how it works and the information it gives back. The series will also demonstrate several real-life applications of how you can put to use these Machine Learning APIs today along and combine them not just with each other but other powerful services within Google Cloud Platform. Specifically, we shall look at Google Cloud Functions, which help us create serverless applications that in combination with Machine Learning APIs provides a next-generation approach to building applications for developers.

What you'll learn-and how you can apply it

  • Understand the Machine Learning APIs available in the Google Cloud Platform
  • Learn how you can employ powerful APIs for Sentiment Analysis, Vision, Video and Speech
  • Utilize Google Cloud Functions, the FaaS offering on Google Cloud Platform
  • Understand via multiple applications, how you can use the APIs to write your own applications
  • Learn about other services in the Google Cloud Platform and how they can be combined together in a Serverless fashion.

This training course is for you because...

  • You are an experienced developer and want to employ Machine Learning in your applications.
  • You want to get started with the best in class Machine Learning APIs for Sentiment Analysis, Text Analysis, Vision & Video Analysis, Speech to Text and Text to Speech.
  • You would like to employ these models in a cost effective and immediate fashion and not build them from scratch.
  • You know basics of JavaScript and Node.js and would like to give your applications an edge by employing Machine Learning APIs.
  • You want to learn about Google Cloud Platforms FaaS offering : Google Cloud Functions


  • Some familiarity with Google Cloud Platform services
  • Ability to understand at a high level JavaScript code
  • No prior knowledge of Machine Learning is required
  • All code samples will be covered in Node.js (JavaScript) and specifically using the Google Cloud Node.js library.

Recommended Preparation:

Google Cloud (online training)

Node.js (video)

Course Set-up:

About your instructor

  • Romin Irani has 20+ years of experience as a software developer with experience of desktop, server-side and mobile applications. Google Developer Expert for Google Cloud Platform for last 4 years, with a focus on learning and training developers across multiple Google Cloud Platform services. Blogs extensively with developer tutorials on https://www.rominirani.com


The timeframes are only estimates and may vary according to how the class is progressing

Session 1 : Introduction to Google Machine Learning Landscape (20 minutes)

  • Spectrum of Services available under Google Cloud Machine Learning
  • High Level overview of Tensorflow, Cloud Machine Learning and Machine Learning APIs
  • Overview of a list of Machine Learning APIs available today

Session 2 : Setup of Developer Environment (20 minutes)

  • Setting up Google Cloud Platform Project
  • Setting up local Development Environment
  • Overview of Google Cloud Functions

Session 3 : Cloud Vision API (30 minutes)

Google Cloud Vision API enables you to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API.

  • Overview of Cloud Vision API
  • Features available in Vision API
  • Sample application that uses Vision API

Break: 5 mins Q&A: 10 mins

Session 4 : Video Intelligence API (30 minutes)

Google Cloud Video Intelligence API makes videos searchable and discoverable by extracting metadata, identifying key nouns, and annotating the content of the video. Overview of Video Intelligence API

  • Features available in Video Intelligence API
  • Sample application that uses Video Intelligence API

Session 5 : Natural Language API (30 minutes)

Google Natural Language API reveals the structure and meaning of text by offering powerful machine learning models in an easy to use REST API. You can use it to extract information about people, places, events and much more, mentioned in text documents, news articles or blog posts. You can also use it to understand sentiment about your product on social media or parse intent from customer conversations happening in a call center or a messaging app.

  • Overview of Natural Language API
  • Features available in Natural Language API
  • Sample application that uses Natural Language API

Session 6 : Speech to Text and Text to Speech APIs (30 minutes)

Google Cloud Speech API enables you to convert audio to text by applying neural network models in an easy to use API. The API recognizes over 110 languages and variants, to support your global user base.

Google Cloud Text-to-Speech enables developers to synthesize natural-sounding speech with 32 voices, available in multiple languages and variants.

  • Overview of Speech to Text and Text to Speech API
  • Features available
  • Sample application that uses Speech to Text and Text to Speech API

Q&A : 10 mins