Ai-900 2022
Ai-900 2022
Fundamentals
Scott Duffy, Instructor
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
April 2022 Updates
Microsoft Azure AI Fundamentals
Speech Services
Language Services
Decision Services
AI-900 Microsoft Azure AI
Fundamentals
Scott Duffy, Instructor
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
What Do We Mean By “AI”?
The term “Artificial
Intelligence” has
been used to
describe many
things
Oxford Dictionary
artificial intelligence (noun)
/ˌärdəˈfiSHəl inˈteləjəns/
“the theory and development of computer systems able to perform tasks that
normally require human intelligence, such as visual perception, speech recognition,
decision-making, and translation between languages.”
Incorporating
human intelligence
into machines
Artificial General Intelligence
That robot or computer in the movies that can teach itself a new task.
“Call Carol.”
Machine Learning
The study of computer algorithms that improve automatically through experience.
Supervised learning - humans label the data and gives general guidance
Covers things like facial recognition, speech recognition and object recognition.
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Describe AI Workloads and
Considerations (20-25%)
Common AI Workloads
1. Prediction and Demand Forecasting
Prediction and Demand Forecasting
Prediction and Demand Forecasting
Using Machine Learning to Predict
● Give the machine all the relevant data you know
Chatbot: Yes, we have those. Do you want me to hold one aside for you?
User: Yes.
...
AI-900 Microsoft Azure AI
Fundamentals
Scott Duffy, Instructor
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Guiding Principles in AI
The prevalence of
AI causes some
ethical and moral
challenges
Unintended
consequences of
leaving important
decisions to a
computer
Unintended Consequences:
Decisions that are wrong
Decisions that are illegal (or at least, go against your own values)
The data is never bad. No fields have blanks. No fields have accented characters.
All connected systems are functional.
How does the military unmanned drone operate when the GPS is down?
How does the self-driving car operate when an object is approaching from the side
instead of the front or back?
Principle of Privacy and Security
Many countries and regions in the world are developing new standards and laws
to try to protect the data of its citizens. Laws are always slower than technology.
Six Principles Should Guide AI Development
● Fairness
● Reliability and safety
● Privacy and security
● Inclusiveness
● Transparency
● Accountability
Principle of Inclusiveness
How does a voice assistant work for someone who has a speech impediment?
How does a fitness tracker work for someone with a mobility disability?
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Describe fundamental principles
of machine learning on Azure (25-
30%)
Common Machine Learning
Types
Regression
A type of supervised learning
C) On a scale of 1-10, how happy is someone who makes $60,000 per year?
C) On a scale of 1-10, how happy is someone who makes $60,000 per year?
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Core Machine Learning Concepts
Feature is an input
variable
Label is the thing
we’re predicting
Features and Labels in a Dataset
Given a pile of data, you (data scientist) need to determine which bits are relevant
to make decisions on
● Experiment
● Domain knowledge
● Keep in mind the principles of AI
Examples of Data
● First and last name
● Smoker or non-smoker (feature)
● Date of birth (feature)
● Marital status (feature)
● Gender (feature)
● Annual income (feature?)
● Blood type
● Number of children
● …
● Life expectancy (label)
Training the Model
The more input (historical) data you have, the more accurate the results
Divide your available labelled data into training and validation/test datasets
Ie. 1,000,000 rows of data - 500K to train the model, 500K to test the model
Split the training
and validation
datasets randomly
Evaluate the Results - Regression
Use the validation dataset to test the model, and measure how close or far the
actual results are from the predicted results
Accuracy vs precision
AI-900 Microsoft Azure AI
Fundamentals
Scott Duffy, Instructor
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Capabilities of No-Code ML
Azure Machine Learning
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Describe features of computer
vision workloads on Azure
(15-20%)
Computer Vision Features
Image Classification
Car
Object Detection
Object Detection
Optical Character Recognition
Facial Detection and Recognition
Facial Recognition
+ Facial Attributes
are special
categories that
requires approval
AI-900 Microsoft Azure AI
Fundamentals
Scott Duffy, Instructor
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Computer Vision Tools
In Azure, you can
use Computer
Vision service,
or you can use
Cognitive Services
Cognitive Services
includes many
other services
under one umbrella
All services require
a KEY and an
ENDPOINT
Computer Vision Service
Pre-trained ML model
Detect faces
Text recognition
Custom Vision Service
A model that you can build and train
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Describe features of NLP
workloads on Azure (25-30%)
NLP Workload Scenarios
Understands
written and spoken
language
Key Phrase Extraction
Identifying the main points of a document; context
“When I was shovelling snow in my driveway earlier today, I cut my finger. It wasn’t a
deep cut, and I will be ok. But it’s a bit painful. Snow isn’t fun sometimes.”
- Shovelling snow
- Cut my finger
- I will be ok
- A bit painful
- Snow isn’t fun
Entity Recognition
Identifying “entities” of a document; items categorized by type and subtype
“When I was shovelling snow in my driveway earlier today, I cut my finger. It wasn’t a
deep cut, and I will be ok. But it’s a bit painful. Snow isn’t fun sometimes.”
Driveway - location
Can also return
links to wikipedia
for relevant entries
I.e. “snow”
Sentiment Analysis
Pre-built ML model
“I thought the steak here was awesome and the staff was super friendly.”
Vs
“The steak was tough and the service was a bit slow. Not a great experience”.
Language Modeling
Build your own dictionary for terms in your industry
Can detect when text has multiple languages and identify the predominant
language
1. Utterances
2. Entities
3. Intents
Language Service - Utterances
An example of something a user will say:
● Today (DateTime)
● You (subject)
Language Service - Intents
The purpose or goal expressed by the user
Goal: TodayHoursOfOperation
Language Service - Intents
Sometimes, there is no intent
Speech to text
Audio translation
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Conversational AI Solutions
Conversational AI
allows a human and
a computer to talk
Typically called
agents, or bots
Azure Bots can
operate over the
web, email, social
media, and voice
Do You Know You’re Talking to a Bot?
Conversational AI Use Cases
Webchat Bots
● Appear on a website or social media app
Conversational banking
Personal Digital Assistants
OK Google - when is my next appointment?
Yo yo, Bing - tell Mom that I’ll be home this weekend from college
Conversational AI Services
Azure Bot Service
Enterprise-grade chat bots
© 2022 Scott Duffy, softwarearchitect.ca… get the course for these slides at:
http://sjd.ca/ai900
Thank you and best of luck!