stud
bud
Sign up
Log in
Home
Library
Explore
SAT
More
Unit 3.5 Review Quiz Flashcards | StudBud
Explore
/
Unit 3.5 Review Quiz
Unit 3.5 Review Quiz
10 terms
·
StudBud Administration
·
132 plays
Project STEM Unit 3.5 review quiz
Flashcards
10 cards
F
Practice quiz
P
Host live
L
Questions
10
Answers
1
One of the challenges of using neural networks is that we can't see what features the algorithms are picking out
False
True
2
If a supervised learning machine was trained to identify different types of balls we might we use what as labels?
Trucks
Soccer Ball
Football
Hockey puck
Frisbee
Baseball
3
If a supervised learning machine was trained to identify different types of farm animals we might we use what as labels?
cars
sheep
pigs
pizza
cows
chicken
4
Machine learning is one of the most frequently used types of AI algorithms today
False
True
5
Machine learning can use an algorithm to sort objects into different types.
What do we call algorithms that do this?
Recommendation algorithms
Search algorithms
Colorful algorithms
Classification algorithms
6
If we trained Machine Learning 2 identify if a person is sketching ahappy or a sad face, what should the dataset be?
Music about people with happy or sad faces
Both happy and sad face sketches drawn by many different types of people
Only sad face sketches drawn by many different types of people
Only happy face sketches drawn by many different types of people
7
In machine learning, humans provide an AI algorithm w/ labeled data (so the AI can associate the data w/ a specific name
True
False
8
How can humans supervise machine learning?
By providing organized and labeled training data
By making sure to turn computers on and off at appropriate times
By telling the AI exactly what rules or criteria to use, step-by-step
It’s not possible, all machine learning is unsupervised
9
A neural network is a type of machine learning algorithm that passes info from node to node, similar to the human brain.
True
False
10
What should we do after training a machine learning algorithm using a training dataset?
Nothing. We just send it out in the world to do its job , it's now ready!
Print the dataset on paper
Stop using the dataset bc it's impossible to know whether it's accurate
Test it on a different dataset to pick out where it is making mistakes