T-GCPBDML-B - M4 - Machine Learning Options On Google Cloud - ILT Slides

Proprietary + Confidential
Machine Learning
Options on
Google Cloud
Module 4
Google Cloud Big Data and Machine Learning Fundamentals
Introduction
01
01 Big Data and Machine Learning on Google Cloud
02 Data Engineering for Streaming Data
03 Big Data with BigQuery
04 Machine Learning Options on Google Cloud
05 The Machine Learning Workflow with Vertex AI
In the previous two modules of this course, you learned about many data engineering
tools available from Google Cloud such as Dataflow, Pub/Sub, and Looker vs. Data
Studio in module 2 and BigQuery in module 3. Now let’s switch our focus to machine
learning. In the next two modules, you’ll learn ML options provided by Google in
module 4 and the ML workflow in module 5.
Agenda
ML options
Pre-built APIs
AutoML
Custom training
Vertex AI
AI solutions
In this module, we’ll explore the different options Google Cloud offers for building
machine learning models, specifically, we’ll introduce pre-built APIs, AutoML, and
custom training.
Additionally, we will explain how a product called Vertex AI can help solve machine
learning challenges.
In the end, we will introduce the Google Cloud AI solutions from both horizontal
(meaning across industries) and vertical (meaning industry specific) perspectives.
Google is an AI-first company
An AI-first company.
2021 leader in the
Gartner Magic Quadrant for
Cloud AI Developer services
A leader across industries in AI

and ML.
So you might be wondering, “Why should I trust Google for artificial intelligence and
machine learning?”
Google is an AI-first company, and is recognized as a leader across industries

because of its contributions in the fields of artificial intelligence and machine learning.
In 2021 Google was recognized as a leader in the Gartner Magic Quadrant for Cloud
AI Developer services, and in recent years has also received recognition in numerous
annual industry awards and reports.
Google has implemented AI for 10+ years
Natural language
processing
And at Google we’ve been implementing artificial intelligence for over ten years into
many of our critical products, systems, and services.
For example, have you ever noticed how Gmail automatically suggests three
responses to a received message? This feature is called Smart Reply, which uses
artificial intelligence to predict how you might respond. Behind this intelligence is AI
technology known as natural language processing, which is just one example of an
impressive list of technologies that Google scientists and engineers are working on.
We’ll explore these in more depth later in the course.
Google’s goal is to enable every

company to be an AI company
The goal of these technologies is not for exclusive use to only benefit Google
customers. The goal is to enable every company to be an AI company by reducing the
challenges of AI model creation to only the steps that require human judgment or
creativity.
AI in different industries
Scheduling Pricing Inventory planning
So for workers in the travel and hospitality field, this might mean using AI and ML to
improve aircraft scheduling or provide customers with dynamic pricing options. For
retail-sector employees, it might mean using AI and ML to leverage predictive
inventory planning. The potential solutions are endless.
What are the problems in your business

that artificial intelligence and machine
learning might help you solve?
What are the problems in your business that artificial intelligence and machine
learning might help you solve? Take a moment to think about this question before
continuing to the next section.
Options to
02
build ML models
ML options on Google Cloud
01 02 03 04
BigQuery ML Pre-built APIs AutoML Custom training
Use SQL queries Leverage ML A no-code Code your own

to create and models that have solution to build ML environment to
execute machine already been built ML models on have the control
learning models in and trained by Vertex AI. over the ML
BigQuery. Google. pipeline.
Google Cloud offers four options for building machine learning models.
● The first option is BigQuery ML. You’ll remember from an earlier module of this
course that BigQuery ML is a tool for using SQL queries to create and execute
machine learning models in BigQuery. If you already have your data in
BigQuery and your problems fit the pre-defined ML models, this could be your
choice.
● The second option is to use pre-built APIs, which are application
programming interfaces. This option lets you leverage machine learning
models that have already been built and trained by Google, so you don’t have
to build your own machine learning models if you don’t have enough training
data or sufficient machine learning expertise in-house.
● The third option is AutoML, which is a no-code solution, so you can build your
own machine learning models on Vertex AI through a point-and-click interface.
● And finally, there is custom training, through which you can code your very
own machine learning environment, the training, and the deployment, which
gives you flexibility and provides the control over the ML pipeline..
Comparing the four ML options
01 02 03 04

Tabular, image, Tabular, image, Tabular, image,
Data type Tabular
text, and video text, and video text, and video
Training data size Medium to large No data required Small to medium Medium to large
ML and coding
Medium Low Low High
expertise
Flexibility to tune
Medium None None High
hyperparameters
Time to train a model Medium None Medium Long
Let’s compare the four options to help you decide which one to use for building your
ML model.
● Data type: BigQuery ML only supports tabular data while the other three
support tabular, image, text, and video.
● Training data size: Pre-built APIs do not require any training data, while
BigQuery ML and custom training require a large amount of data.
● Machine learning and coding expertise: Pre-Built APIs and AutoML are user
friendly with low requirements, while Custom training has the highest
requirement and BigQuery ML requires you to understand SQL.
● Flexibility to tune the hyperparameters: At the moment, you can’t tune the
hyperparameters with Pre-built APIs or AutoML, however, you can experiment
with hyperparameters using BigQueryML and custom training.
● Time to train the model: Pre-built APIs require no time to train a model
because they directly use pre-built models from Google. The time to train a
model for the other three options depends on the specific project. Normally,
custom training takes the longest time because it builds the ML model from
scratch, unlike AutoML and BigQuery ML.
AutoML uses a backend technology called Transfer Learning (you’ll learn it in
the later section), meaning to train a new ML model based on existing training results
to speed the model training time. Custom training, compared to AutoML, has to train
a model from scratch, which normally takes longer time.
How to decide on the right ML option
Familiar with SQL and have

data in BigQuery
01 BigQuery ML
Have little ML expertise 02 Pre-built APIs
Want to build custom models

with your own training data 03 AutoML
with minimal coding
Want full control of the

ML workflow
04 Custom training
Selecting the best option will depend on your business needs and ML expertise.
- If your data engineers, data scientists, and data analysts are familiar with SQL
and already have your data in BigQuery, BigQuery ML lets you develop
SQL-based models.
- If your business users or developers 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 are ready to use without any
ML expertise or model development effort.
- If your developers and data scientists want to build custom models with your
own training data while spending minimal time coding, then AutoML is your
choice. AutoML provides a code-less solution to enable you to focus on
business problems instead of the underlying model architecture and ML
provisioning.
- If your ML engineers and data scientists want full control of ML workflow,
Vertex AI custom training lets you train and serve custom models with code on
Vertex Workbench.
Focus in this module
01 02 03 04

execute machine already been built ML models on have full control
learning models in and trained by Vertex AI. over the entire
BigQuery. Google. process.
We’ve already explored BigQuery ML, so in the videos that follow, we’ll explore the
other three options in more detail.
03 Pre-built APIs
Pre-built APIs don’t require custom training data
Offered as services
Build datasets
Pre-built APIs Curate datasets
Traine datasets
Good Machine Learning models require lots of high-quality training data. You should
aim for hundreds of thousands of records to train a custom model. If you don't have
that kind of data, pre-built APIs are a great place to start.
Pre-built APIs are offered as services. In many cases they can act as building blocks
to create the application you want without expense or complexity of creating your
own models. They save the time and effort of building, curating, and training a new
dataset so you can just jump right ahead to predictions.
Pre-built API examples
Speech-to-Text API Converts audio to text for data processing.
Cloud Natural Language API Recognizes parts of speech called entities and sentiment.
Cloud Translation API Converts text from one language to another.
Text-to-Speech API Converts text into high-quality voice audio.
Vision API Works with and recognizes content in static images.
Video Intelligence API Recognizes motion and action in video.
So, what are some of the pre-built APIs? Let’s explore a short list.
● The Speech-to-Text API converts audio to text for data processing.

● The Cloud Natural Language API recognizes parts of speech called entities
and sentiment.
● The Cloud Translation API converts text from one language to another.
● The Text-to-Speech API converts text into high quality voice audio.
● The Vision API works with and recognizes content in static images.
● And the Video Intelligence API recognizes motion and action in video.
Pre-built APIs trained with Google datasets
Vision API Speech-to-Text API Translation API
Based on Trained on Built on
Google’s image datasets YouTube captions Google Translate
And Google has already done a lot of work to train these models using Google
datasets. For example,
● the Vision API is based on Google’s image datasets,
● the Speech-to-Text API API is trained on YouTube captions,
● and the Translation API is built on Google Translate.
You’ll recall that how well a model is trained depends on how much data is available
to train it. As you might expect, Google has a lot of images, text, and ML researchers
to train it’s pre-built models. This means less work for you.
Vision API
cloud.google.com/vision
Let’s take a minute and try out the Vision API in a browser. Start by navigating to
cloud.google.com/vision in Chrome,
And then scroll down to try the API by uploading an image.
You can actually experiment with each of the ML APIs in a browser.
When you’re ready to build a production model, you’ll need to pass a JSON object
request to the API and parse what it returns.
AutoML
04
Traditional ML development vs. AutoML
Traditional ML development AutoML: Automated machine learning

(2018)
Repeatedly add new data and features Automates machine learning

pipelines to save data scientists from
Try different models manual work
Tune hyperparameters
To understand AutoML, which is short for automated machine learning, let’s briefly
look at how it was built.
If you've worked with ML models before, you know that training and deploying ML
models can be extremely time consuming, because you need to repeatedly add new
data and features, try different models, and tune parameters to achieve the best
result.
To solve this problem, when AutoML was first announced in January of 2018, the goal
was to automate machine learning pipelines to save data scientists from manual
work, such as tuning hyperparameters and comparing against multiple models.
Machine learning is similar to human learning
But how could this be done? Well, machine learning is similar to human learning. It all
starts with gathering the right information.
Transfer learning
Build a knowledge base in the field
For AutoML, two technologies are vital. The first is known as transfer learning. With
transfer learning, you build a knowledge base in the field. You can think of this like
gathering lots of books to create a library.
Transfer learning from pre-trained models
Transfer learning
Transfer learning is a powerful technique that lets people with smaller datasets, or
less computational power, achieve state-of-the-art results by taking advantage of
pre-trained models that have been trained on similar, larger data sets. Because the
model learns via transfer learning, it doesn’t have to learn from scratch, so it can
generally reach higher accuracy with much less data and computation time than
models that don’t use transfer learning.
Neural Architect Search finds the optimal model
Neural Architect Search
The second technology is neural architect search.The goal of neural architect search
is to find the optimal model for the relevant project. Think of this like finding the best
book in the library to help you learn what you need to.
AutoML
Powered by the latest ML research
Trains and evaluates multiple models
Produces an ensemble of ML models
Chooses the best one
AutoML is powered by the latest machine-learning research, so although a model

performs training, the AutoML platform actually trains and evaluates multiple models
and compares them to each other. This neural architecture search produces an
ensemble of ML models and chooses the best one.
Leveraging these technologies has produced a tool that can significantly benefit data
scientists.
Benefits of AutoML
Train custom ML models with
Minimal effort
Little machine learning expertise
Allows data scientists to focus on
Defining business problems
Evaluating and improving model results
One of the biggest benefits is that it’s a no-code solution.That means it can train
high-quality custom machine learning models with minimal effort and requires little
machine learning expertise.
This allows data scientists to focus their time on tasks like defining business
problems or evaluating and improving model results.
Others might find AutoML useful as a tool to quickly prototype models and explore
new datasets before investing in development. This might mean using it to identify
the best features in a dataset, for example.
AutoML supports four types of data
Image Tabular
AutoML solves different
types of problems, called
objectives
Text Video
So, how does AutoML work exactly? AutoML supports four types of data: image,
tabular, text, and video. For each data type, AutoML solves different types of
problems, called objectives.
To start, upload your data into AutoML
Cloud Storage BigQuery
Local machine
To get started, upload your data into AutoML. It can come from Cloud Storage,
BigQuery, or even your local machine.
Inform AutoML of the problems you want to solve
Inform AutoML of problems to solve
Inform AutoML
May sound of thetoproblems
similar pre-built APIs
Pre-built APIs AutoML
Use pre-built Uses custom-built

ML models ML models
From there, inform AutoML of the problems you want to solve.
Some problems may sound similar to those mentioned in pre-built APIs. However the
major difference is that pre-built APIs use pre-built machine learning models, while
AutoML uses custom-built models. In AutoML, you use your own data to train the
machine learning model and then apply the trained model to predict your goal. While
in pre-built APIs, the models are already trained with Google’s datasets. You take the
advantage of the training results to predict your data.
Image data objectives
Use a classification model to analyze image

data and return a list of content categories
that apply to the image.
Image data
Use an object detection model to analyze
your image data and return annotations that
consist of a label and bounding box location
for each object found in an image.
For image data:
● You can use a classification model to analyze image data and return a list of
content categories that apply to the image. For example, you could train a
model that classifies images as containing a dog or not containing a dog, or
you could train a model to classify images of dogs by breed.
● You can also use an object detection model to analyze your image data and
return annotations that consist of a label and bounding box location for each
object found in an image. For example, you could train a model to find the
location of the dogs in image data.
Tabular data objectives

Use a regression model to analyze tabular
data and return a numeric value.
Use a classification model to analyze tabular

data and return a list of categories.
Tabular data
A forecasting model can use multiple rows of

time-dependent tabular data from the past to
predict a series of numeric values in the future.
For tabular data:
● You can use a regression model to analyze tabular data and return a numeric
value. For example, you could train a model to estimate a house’s value or
rental price based on a set of factors such as location, size of the house, and
number of bedrooms.
● You can use a classification model to analyze tabular data and return a list of
categories. For example, you could train a model to classify different types of
land into high, median, and low potentials for commercial real estate.
● And a forecasting model can use multiple rows of time-dependent tabular
data from the past to predict a series of numeric values in the future. For
example, you could use the historical plus the economic data to predict what
the housing market will look like in the next five years.
Text data objectives

Use a classification model to analyze text
data and return a list of categories that apply
to the text found in the data.
An entity extraction model can be used to

inspect text data for known entities
referenced in the data and label those
Text data entities in the text.
A sentiment analysis model can be used to

inspect text data and identify the prevailing
emotional opinion within it.
For text data:
● You can use a classification model to analyze text data and return a list of
categories that apply to the text found in the data. For example, you can
classify customer questions and comments to different categories and then
redirect them to corresponding departments.
● An entity extraction model can be used to inspect text data for known entities
referenced in the data and label those entities in the text. For example, you can
label a social media post in terms of predefined entities such as time, location,
and topic, etc. This can help with online search, similar to the concept of a
hashtag, but created by machine.
● And a sentiment analysis model can be used to inspect text data and identify
the prevailing emotional opinion within it, especially to determine a writer's
comment as positive, negative, or neutral.
Video data objectives

Use a classification model to analyze video
data and return a list of categorized shots
and segments.
Use an object tracking model to analyze

video data and return a list of shots and
segments where these objects were
Video data detected.
An action recognition model can be used to

analyze video data and return a list of
categorized actions with the moments the
actions happened.
And finally, for video data:
● You can use a classification model to analyze video data and return a list of
categorized shots and segments. For example, you could train a model that
analyzes video data to identify whether the video is of a soccer, baseball,
basketball, or football game.
● You can use an object tracking model to analyze video data and return a list of
shots and segments where these objects were detected. For example, you
could train a model that analyzes video data from soccer games to identify
and track the ball.
● And an action recognition model can be used to analyze video data and return
a list of categorized actions with the moments the actions happened. For
example, you could train a model that analyzes video data to identify the
action moments involving a soccer goal, a golf swing, a touchdown, or a high
five.
AutoML solves mixed data types and objectives
Image Tabular
AutoML Text Video
In reality, you may not be restricted to just one data type and one objective but rather
need to combine different objectives to solve a business problem.
AutoML is a powerful tool that can help across these different data types and
objectives.
Custom training
05
01 02 03 04

execute machine already been built ML models on have full control
learning models in and trained by Vertex AI. over the entire
BigQuery. Google. process.
We’ve explored the options Google Cloud provides to build machine learning models
using BigQuery ML, pre-built APIs, and AutoML. Now let's take a look at the last
option, custom training, which allows you to code your own ML environment to have
full control over the entire ML development process starting from data preparation to
model deployment.
Vertex AI Workbench
Single development Vertex AI

environment Workbench
If you want to code your machine learning model, you can use this option by building a
custom training solution with Vertex AI Workbench.
Workbench is a single development environment for the entire data science workflow,
from exploring, to training, and then deploying a machine learning model with code.
ML training code environment options
1 A pre-built container
A custom container
Before any coding begins, you need to determine what environment you want your ML
training code to use. There are two options: a pre-built container or a custom
container.
A pre-built container is like a fully furnished room
Imagine that a container is a kitchen. A pre-built container would represent a fully

furnished room with cabinets and appliances (which represent the dependencies) that
includes all the cookware (which represents the libraries) you need to make a meal.
Pre-built containers: Pre-installed environment
Tensorflow
Pytorch
Scikit-learn
Pre-built
XGboost container
Python code
So, if your ML training needs a platform like Tensorflow, Pytorch, Scikit-learn, or

XGboost, and Python code to work with the platform, a pre-built container is probably
your best solution.
A custom container is like an empty room
Empty room > Custom container
A custom container, alternatively, is like an empty room with no cabinets, appliances,

or cookware.
Custom container: Define your own environment
Custom
container
You define the exact tools that you need to complete the job.
06
Vertex AI
Google’s AI technologies and products
2007 2015 2018 2019 2021
Scikit Learn Tensorflow 1.0 Tensorflow 2.0
Technology Technology Technology
AutoML
BigQuery ML AI Platform Vertex AI
Product Product Product
For years now, Google has invested time and resources into developing big data and
AI. Google had developed key technologies and products, from its roots in the
development of Scikit Learn back in 2007 to Vertex AI today.
AI challenges: ML development
Data
Machine learning models
Computing power
As an AI-first company, Google has applied AI technologies to many of its products

and services, like Gmail, Google Maps, Google Photos, and Google Translate, just to
name a few. But developing these technologies doesn’t come without challenges,
especially when it involves developing machine learning models and putting them
into production.
Some traditional challenges include determining how to handle large quantities of

data, determining the right machine learning model to train the data, and harnessing
the required amount of computing power.
AI challenges: ML production
Only half of enterprise ML projects Scalability
get past the pilot phase. Monitoring
"Gartner Identifies the Top Strategic Technology trends for 2021” Continuous integration and continuous
- Gartner press release, October 19, 2020 delivery or deployment
Then there are challenges around getting ML models into production. Production
challenges require scalability, monitoring, and continuous integration and continuous
delivery or deployment.
In fact, according to Gartner, only half of enterprise ML projects get past the pilot
phase.
AI challenges: ML tools ease-of-use
Tools require advanced coding skills
Take focus away from model configuration
No unified workflow
Difficulties finding tools
And finally, there are ease-of-use challenges. Many tools on the market require
advanced coding skills, which can take a data scientist’s focus away from model
configuration. And without a unified workflow, data scientists often have difficulties
finding tools.
Google’s solution is Vertex AI
Production Ease-of-use
challenges challenges
Vertex AI
Google’s solution to many of the production and ease-of-use challenges is Vertex AI,
a unified platform that brings all the components of the machine learning ecosystem
and workflow together.
Vertex AI is a unified platform
Create models Manage models Deploy models
Training and Deployment and model

Data readiness Feature readiness
hyperparameter tuning monitoring
Users can upload data from Users can create features, When the data is ready, users Users can set up the pipeline
wherever it’s stored–Cloud which are the processed data can experiment with different to transform the model into
Storage, BigQuery, or a that will be put into the models and adjust production by automatically
local machine. model, and then share them hyperparameters. monitoring and performing
with others using the feature continuous improvements.
store.
So, what exactly does a unified platform mean? In the case of Vertex AI, it means
having one digital experience to create, manage, and deploy models over time, and at
scale. For example,
● During the data readiness stage, users can upload data from wherever it’s
stored– Cloud Storage, BigQuery, or a local machine.
● Then, during the feature readiness stage, users can create features, which are
the processed data that will be put into the model, and then share them with
others using the feature store.
● After that, it’s time for Training and Hyperparameter tuning. This means that
when the data is ready, users can experiment with different models and adjust
hyperparameters.
● And finally, during deployment and model monitoring, users can set up the
pipeline to transform the model into production by automatically monitoring
and performing continuous improvements.
Vertex AI provides two solutions in one
1 AutoML: no-code solution
Custom training: code-based solution
Vertex AI
And to refer back to the different options we explored earlier, Vertex AI allows users to
build machine learning models with either AutoML, a code-less solution or Custom
Training, a code-based solution. AutoML is easy to use and lets data scientists spend
more time turning business problems into ML solutions, while custom training
enables data scientists to have full control over the development environment and
process.
The benefits of Vertex AI
Seamless Sustainable
Scalable Speedy
Vertex AI
Being able to perform such a wide range of tasks in one unified platform has many
benefits. This can be summarized with four Ss:
- It’s seamless. Vertex AI provides a smooth user experience from uploading
and preparing data all the way to model training and production.
- It’s scalable. The Machine Learning Operations (MLOps) provided by Vertex AI
helps to monitor and manage the ML production and therefore scale the
storage and computing power automatically.
- It’s sustainable. All of the artifacts and features created using Vertex AI can be
reused and shared.
- And it’s speedy. Vertex AI produces models that have 80% fewer lines of code
than competitors.
07 AI solutions
Google’s AI solution portfolio
Horizontal solutions Vertical/Industry solutions

AI solutions Retail Product Healthcare Lending
Document AI CCAI
Discovery Data Engine DocAI
AI development Vertex AI:

Vertex AI:
Custom Pre-built APIs BigQuery ML
AutoML
platform training
Infrastructure Data
AI foundation Compute, storage, networking BigQuery, Dataflow, Looker
Now that you’ve explored the four different options available to create machine
learning models with Google Cloud, let’s take a few minutes to explore Google
Cloud’s artificial intelligence solution portfolio.
It can be visualized with three layers.

● The bottom layer is the AI foundation, and includes the Google Cloud
infrastructure and data.
● The middle layer represents the AI development platform, which includes the
four ML options you just learned about: AutoML and custom training, which
are offered through Vertex AI, and pre-built APIs and BigQuery ML.
● The top layer represents AI solutions, for which there are two groups,
horizontal solutions and industry solutions.

Document AI CCAI

Vertex AI:
AutoML
platform training
Infrastructure Data
Horizontal solutions usually apply to any industry that would like to solve the same
problem.
Examples include Document AI and CCAI.

● Document AI uses computer vision and optical character recognition, along
with natural language processing, to create pretrained models to extract
information from documents. The goal is to increase the speed and accuracy
of document processing to help organizations make better decisions faster,
while reducing costs.
● Another example of a horizontal solution is Contact Center AI, or CCAI. The
goal of CCAI is to improve customer service in contact centers through the use
of artificial intelligence. It can help automate simple interactions, assist human
agents, unlock caller insights, and provide information to answer customer
questions.

Document AI CCAI

Vertex AI:
AutoML
platform training
Infrastructure Data
And the second group is vertical, or industry solutions. These represent solutions that
are relevant to specific industries.
Examples include:
● Retail Product Discovery, which gives retailers the ability to provide
Google-quality search and recommendations on their own digital properties,
helping to increase conversions and reduce search abandonment,
● Google Cloud Healthcare Data Engine, which generates healthcare insights
and analytics with one end-to-end solution, and
● Lending DocAI, which aims to transform the home loan experience for
borrowers and lenders by automating mortgage document processing.
cloud.google.com/solutions/ai
You can learn more about Google Cloud’s growing list of AI solutions at
cloud.google.com/solutions/ai.
Summary
08
Let’s review
ML options
Pre-built APIs
AutoML
Custom training
Vertex AI
AI solutions
We’ve covered a lot of information in this module of the course. Let’s do a quick
recap.
To start, we explored Google’s history as an AI-first company. From there, we looked at

the four options Google Cloud offers to build machine learning models, BigQuery ML,
pre-built APIs, AutoML, and Custom Training. We focused on the latter three in this
module.
Next, we introduced Vertex AI, a tool that combines the functionality of AutoML, which
is codeless, and custom training, which is code-based, to solve production and
ease-of-use problems.
And finally, we introduced Google Cloud AI solutions.

ML options on Google Cloud
Familiar with SQL and have

data in BigQuery
01 BigQuery ML
Have little ML expertise 02 Pre-built APIs
Want to build custom models

with your own training data 03 AutoML
with minimal coding
Want full control of the

ML workflow
04 Custom training
You’ll recall that selecting the best ML option will depend on your business needs and
ML expertise.
- If your data engineers, data scientists, and data analysts are familiar with SQL
and already have your data in BigQuery, BigQuery ML lets you develop
SQL-based models.
- If your business users or developers 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 are ready to use without any
ML expertise or model development effort.
- If your developers and data scientists want to build custom models with your
own training data while spending minimal time coding, then AutoML is your
choice. AutoML provides a code-less solution to enable you to focus on
business problems instead of the underlying model architecture and ML
provisioning.
- If your ML engineers and data scientists want full control of ML workflow,
Vertex AI custom training lets you train and serve custom models with code on
Vertex Workbench.

Document AI CCAI

Vertex AI:
AutoML
platform training
Infrastructure Data
The Google AI solutions are built on top of the four ML development options to meet
both horizontal and vertical market needs.

T-GCPBDML-B - M4 - Machine Learning Options On Google Cloud - ILT Slides

Uploaded by

Copyright:

Available Formats

T-GCPBDML-B - M4 - Machine Learning Options On Google Cloud - ILT Slides

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

T-GCPBDML-B - M4 - Machine Learning Options On Google Cloud - ILT Slides

Uploaded by

Copyright:

Available Formats

Proprietary + Confidential

01 Big Data and Machine Learning on Google Cloud

02 Data Engineering for Streaming Data

03 Big Data with BigQuery

04 Machine Learning Options on Google Cloud

05 The Machine Learning Workflow with Vertex AI

Google is an AI-first company

A leader across industries in AI

Google is an AI-first company, and is recognized as a leader across industries

Google has implemented AI for 10+ years

Google’s goal is to enable every

Scheduling Pricing Inventory planning

What are the problems in your business

ML options on Google Cloud

BigQuery ML Pre-built APIs AutoML Custom training

Use SQL queries Leverage ML A no-code Code your own

Comparing the four ML options

BigQuery ML Pre-built APIs AutoML Custom training

Time to train a model Medium None Medium Long

How to decide on the right ML option

Familiar with SQL and have

Have little ML expertise 02 Pre-built APIs

Want to build custom models

Want full control of the

Focus in this module

BigQuery ML Pre-built APIs AutoML Custom training

Use SQL queries Leverage ML A no-code Code your own

Pre-built APIs don’t require custom training data

Pre-built APIs Curate datasets

Pre-built API examples

Speech-to-Text API Converts audio to text for data processing.

Cloud Translation API Converts text from one language to another.

Text-to-Speech API Converts text into high-quality voice audio.

Vision API Works with and recognizes content in static images.

Video Intelligence API Recognizes motion and action in video.

● The Speech-to-Text API converts audio to text for data processing.

Pre-built APIs trained with Google datasets

Vision API Speech-to-Text API Translation API

Based on Trained on Built on

Google’s image datasets YouTube captions Google Translate

And then scroll down to try the API by uploading an image.

You can actually experiment with each of the ML APIs in a browser.

Traditional ML development vs. AutoML

Traditional ML development AutoML: Automated machine learning

Repeatedly add new data and features Automates machine learning

Machine learning is similar to human learning

Build a knowledge base in the field

Transfer learning from pre-trained models

Neural Architect Search finds the optimal model

Neural Architect Search

Powered by the latest ML research

Trains and evaluates multiple models

Produces an ensemble of ML models

Chooses the best one

AutoML is powered by the latest machine-learning research, so although a model

Train custom ML models with

Little machine learning expertise

Allows data scientists to focus on

Defining business problems