Lesson 3.5: Check for Understanding

Machine learning is one of the most frequently used types of AI algorithms today.

• True

• False

In supervised machine learning, humans provide an AI algorithm with labeled data (so the AI can associate the data with a specific name or class).

• True

• False

If we were training a supervised machine learning algorithm to identify different types of balls, what might we use as labels for the different classes? (Select all correct answers.)

• Soccer ball

• Baseball

• Trucks

• Football

• Clouds

If we were training a supervised machine learning algorithm to identify different types of farm animals what might we use as labels for the different classes? (Select all correct answers.)

• Cow

• Sheep

• Cars

• Chicken

• Pizza

How can humans supervise machine learning?

• By making sure to turn computers on and off at appropriate times

• By providing organized and labeled training data

• By telling the AI exactly what rules or criteria to use, step-by-step

• It's not possible, all machine learning is unsupervised

Supervised machine learning can use an algorithm to sort objects into different types – such as sorting marshmallows from cereal, or cats from dogs. What do we call algorithms that do this?

• Recommendation algorithms

• Classification algorithms

• Colorful algorithms

• Search algorithms

If we wanted to train a machine learning algorithm to identify whether a person is sketching a happy or a sad face, what should the dataset we use contain – to make sure it is diverse?

• Both happy and sad face sketches drawn by many different types of people

• Only happy face sketches drawn by many different types of people

• Only sad face sketches drawn by many different types of people

• Music about people with happy or sad faces

What should we do after training a machine learning algorithm using a training dataset?

• Nothing. We should just send it out in the world to do its job — it's now ready!

• Print the dataset on paper.

• Test it on a different dataset (without labels) to pick out where it is making mistakes

• Stop using the dataset because it's impossible to know whether it's accurate or not.

A neural network is a type of machine learning algorithm that passes information from node to node, similar to the human brain.

• True

• False

One of the challenges of using neural networks is that we can’t see what features the algorithms are picking out – a concept called a “black box”.

• True

• False