Embedded Files
In this next assignment you will uncover A.I.'s special power, machine learning.
After completion of this assignment, you should be able to apply the problem solving process to train a computer to solve a problem
Essential questions: How can we use the problem solving process to solve a problem with machine learning? What is a situation where it it might be helpful to use machine learning to solve a problem?
In this assignment you will be working on your own.
Can a machine play Pictionary and guess what you are trying to draw? Spend a few minutes playing Quick Draw!.
What did Quick, Draw! guess correctly? What did Quick Draw! guess incorrectly? Why do you think Quick Draw! guessed some things correctly and some things incorrectly?
GIF source: Free Game Planet
Quick Draw! was made by Google. It is a fun activity created using machine learning. You draw something, and a computer program tries to figure out what it is. It doesn't always get it right, but the more you play, the better it becomes at guessing. It's a cool way to see how machine learning can be used for fun.
What is machine learning? How does Quick Draw! guess what you are drawing?
Watch the video below.
Machine learning is how computers learn to recognize patterns and make decisions without being specifically programmed.
Machine learning assists us in addressing significant challenges in our community. You will explore ways to develop machine learning applications to tackle problems. To guide your efforts, you will follow the Problem Solving Process - Define, Prepare, Try, Reflect, and always consider Empathy.
Source: Code.org
In our everyday lives, problem-solving is like finding better ways to do things. Let's say your mornings feel a bit rushed, and you wish you had more time. That's the problem we want to solve. So, first, we figure out exactly what's causing the rush. We gather data such as tracking the time spent on different tasks during the morning routine. Then, we make a plan—a new morning routine. We try it out for a week and see if it helps. Did it make things smoother and less stressful? We reflect on what worked and what didn't. Throughout this process, we always think about the people involved, making sure the solution works for everyone.
And there you go, that's problem-solving in action!
Now, let's see how these steps apply specifically to machine learning.
In this activity, you will use A.I. for Oceans in Code.org. You are going to use machine learning to help a robot, A.I. Bot, clean up the ocean and learn how to identify fish. You will give it lots of examples of fish, give it time to learn from those examples, and then see how well it does in cleaning up the ocean.
Click here to make a copy of the Activity Guide. You will use this guide to record your observations and findings as you are training A.I. Bot.
GIF source: Code.org
Log on to Code.org You should see your assignments on your Dashboard.
Start with Level 1. This level guides you through the process of training A.I. Bot to recognize fish. As you do, fill in the first part of the activity guide. Did the A.I. Bot identify some trash as fish? If we wanted A.I. Bot to become better at recognizing fish, how do you think we could help it do that?
What you have done is an example of how the problem solving process and machine learning can be used to solve a problem. We prepared our data, used it to train A.I. Bot, then reflected on the results and decided what to do next.
Continue with Level 2 - Recognizing Fish Features. In this next level, you will follow the same process and train A.I. Bot to detect certain kinds of fish by its color or body type. Choose what you want to train A.I. Bot to recognize, and record this information on your Activity Guide. When you reach the final stage, press the white Information icon in the upper-right corner.
Information icon
This displays the features that A.I. Bot is using to help make its decision. What features did A.I. Bot think were the most important? Are those the features you were expecting to be most important?
4. Level 3 - Recognizing Fish Expressions. This level lets you train A.I. Bot to recognize a fish by its expression, such as “silly” or “serious” or “angry”. Choose an expression that you want to train A.I. Bot to recognize, and record this information on your Activity Guide. On the final screen, press the information icon and record the features that A.I. Bot learned were most important. Are those the features you were expecting to be most important? How could you help A.I. Bot continue to improve how it makes its decision? Record your findings in the Activity Guide.
5. Submit your completed Activity Guide in Google Classroom.
Image from Unsplash.com
Great job on completing your machine learning experience! In this activity, you conducted supervised machine learning by guiding the computer's training, gaining insight into how computers learn through examples. This process is similar to parents teaching colors to a toddler, wherein machines learn from labeled examples, much like parents pointing to a colored object in a book and saying "brown bear" or "red bird."
Now, with your newfound understanding of machine learning, can you explain how Quick Draw! makes guesses based on what is being drawn? Additionally, reflect on examples of machine learning in everyday A.I. applications that you use or encounter regularly. How is it used in face detection? handwriting detection?
In the upcoming step, you'll discover the limitations of machine learning. Ready?
Page updated
Google Sites
Report abuse