How Does Machine Learning Work?

Machine Learning Review

Learning Objective

Students will review how machine learning terminology and how it functions.

DOL

Given a quiz using Blooket, SWBAT answer at least 10/12 questions with at least 88% accuracy.

Review

• What is a chatbot?

• What is a virtual assistant.

• How do you set up email to recognize spam?

• How does a computer learn?

• What should you do to make sure your email is sending the correct email to the spam folder?

• What are your thoughts about the future of artificial intelligence?

• Random - What do you think about Governor Abbot's decision asking people to no longer wear masks?

Open Ended

What is one interesting fact about machine learning did you learn from this video?

Vocabulary

• chatbot - software applications that allows for written communication between customer and agent

• virtual assistant - is a self-employed worker who specializes in offering services to clients from a remote location

Vocabulary

• turing test - determines whether or not a computer can think like a human

• algorithms -a set of rules to be followed in calculations for a computer

Vocabulary

• machine learning - is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

• autonomous car - a driverless vehicle

Vocabulary

• neural networks - systems of artificial neurons that use data to determine patterns

• autonomous car - a driverless vehicle

• In a machine learning sort of approach, I’d show you lots of examples of kicking a ball.

  Maybe examples of different people kicking a ball.

  
  

  
  

• Maybe even kicking different types of ball.

  Instead of telling you what to do, I’d get you to learn from the collected examples of people who are already able to kick a ball.

  
  

Continued

• Imagine you wanted to make your own email spam filter for school.

• You break down recognizing spam emails into a series of steps that a computer can follow – what we’d describe as a rules-based approach.

Continued

• Let’s say that you get an email like this with a Nigerian scam. So you add a rule to your program that says block any email that mentions Nigeria is spam.

  
  

• But that ends up binging your teacher's email about a possible Geography project on Nigeria.

  
  

Continued

• Let’s say that you get an email like this with a Nigerian scam. So you add a rule to your program that says block any email that mentions Nigeria is spam.

• But that ends up binging your teacher's email about a possible Geography project on Nigeria.

• So you go back to your rules and change it so that only emails that mention Nigeria and money are spam.

Continued

• As the set of rules get bigger and bigger and bigger over time, it becomes really difficult to manage. New rules you add will contradict or break rules that you added a month ago.

• You start again, and this time you use machine learning. You collect a set of examples of emails that you get. You read through them, and sort them into two piles.

  
  

Emails

• Spam emails in one pile. Legitimate not-spam emails in the other.

  You use these examples to train the computer to be able to recognize what a spam email looks like.

  
  

• If every spam email in the spam pile was a Nigerian scam email, and there were no emails in the not-spam pile that included a reference to Nigeria, then there is a reasonable chance that the computer could learn that references to Nigeria mean an email is spam.

  
  

Other Applications: Machine learning is all around us. You use machine learning systems every day.

• Spam filters are a good example.

• So are assistants like Siri, Google Now and Alexa.

• Systems that translate one language to another – trained on examples of documents that have been manually translated.

• The auto-suggest on my phone keyboard, that suggests what word I might want to write next .

Other Applications: Machine learning is all around us. You use machine learning systems every day.

• Spam filters are a good example.

• So are assistants like Siri, Google Now and Alexa.

• The auto-suggest on my phone keyboard, that suggests what word I might want to write next.

• Credit card fraud detection – trained on my buying patterns to recognise a purchase that might not actually be me.

  
  

Multiple Choice

Ms. Taylor needs to send a message to one of her students to turn his camera on. Which would she use to communicate with the student?

• Send an email

• Use the chatbox.

• use the annotation tool

• Type it across the screen on the zoom call.

Multiple Choice

Which test was designed to see if a computer could think like a human.

• The McCarthy Test

• The STAAR Test

• The Alan Test

• The Touring Test

Multiple Choice

Uriel uses a step by step approach to solve a scientific equation. This also called.....

• an algorithm

• a problem solving strategy

• the scientific method

• UPS check

Multiple Choice

This works like a human's brain and it's what causes the computer to function like a human.

• facial recognition

• supervised learning

• expert system

• neural network

Multiple Choice

Pablo wants to train his computer to recognize the difference between an orange and a watermelon. What does Pablo need to do?

• Show a picture of a watermelon and an orange only once.

• Eat a watermelon and an orange while the computer watches on.

• Provide the computer an example of both over and over until it's able to recognize each fruit.

• Verbally keep telling the computer which is which over and over.

Multiple Select

If you want to train your computer to not deliver spam mail to your inbox, which steps should you follow? (Check all that apply.)

• sort through the emails and give examples of spam

• do the process only once

• allow the computer to follow the process multiple times until it can function without help.

• Train the computer on certain words that signal this email maybe spam.

Multiple Choice

Siri, Cortana, and Alexa are examples of.....

• chat boxes

• supervised learning

• virtual assistants

• live assistants

Multiple Select

Which steps should be following to train your computer to place unwanted emails in the spam folder? (Check all that apply.)

• Allow the computer to follow the process of recognizing spam mail only once.

• Develop piles which separate acceptable emails from unwanted emails using key words.

• Repeat the process multiple times until the computer can function on its own.

• Never label the email as spam..