Machine Learning for Kids Worksheet
AI tip (Show, label, learn): Machine learning learns patterns from many labelled examples — a label is the right answer tag on each example. Good for training: many varied examples, correct labels, every type the model will meet, and separate new data for testing. Bad for training: very few examples, wrong or random labels, only one kind of example, blurry examples, testing on the training data.
NameDateTime takenScore ___ / 40
- 1.🥭 A model saw only ripe yellow mangoes. A raw green mango arrives. What may happen? (a) it will turn yellow (b) it may get it wrong (c) it will shut down (d) it will be perfect
- 2.📚 Good or bad for training a model: wrong labels? (a) good for training (b) bad for training
- 3.True or false: “wrong labels” is good for training a model. (a) False (b) True
- 4.True or false: the message “Send your password to claim a prize” should be labelled “spam”. (a) False (b) True
- 5.True or false: the message “The class picnic is on Friday at 8 am” should be labelled “spam”. (a) False (b) True
- 6.Which of these is bad for training a model? (a) many varied examples (b) clear, sharp examples (c) checking labels twice (d) testing on training data
- 7.True or false: “testing on training data” is good for training a model. (a) True (b) False
- 8.True or false: the message “Please buy milk on the way home” should be labelled “spam”. (a) True (b) False
- 9.📚 Usually, more good examples make a model… (a) change colour (b) forget everything (c) slower to switch on (d) better at its task
- 10.📚 Good or bad for training a model: photos in many lights? (a) bad for training (b) good for training
- 11.Which of these is good for training a model? (a) blurry, unclear photos (b) very few examples (c) examples of every type (d) copies of one photo
- 12.🏷️ What is a “label” in machine learning? (a) the price (b) a sticker on a laptop (c) the font size (d) the right answer tag
- 13.Which of these is bad for training a model? (a) clear, sharp examples (b) checking labels twice (c) labels added at random (d) many varied examples
- 14.🔍 Which is the odd one out? (a) blurry, unclear photos (b) many varied examples (c) labels added at random (d) wrong labels
- 15.True or false: “checking labels twice” is bad for training a model. (a) True (b) False
- 16.🔍 Which is the odd one out? (a) very few examples (b) new data for testing (c) labels added at random (d) copies of one photo
- 17.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Last chance! Free gift card inside” (a) not spam (b) spam
- 18.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “The class picnic is on Friday at 8 am” (a) not spam (b) spam
- 19.True or false: “many varied examples” is bad for training a model. (a) True (b) False
- 20.True or false: the message “Science project groups are on the board” should be labelled “spam”. (a) True (b) False
- 21.Which of these is good for training a model? (a) labels added at random (b) testing on training data (c) correct labels (d) copies of one photo
- 22.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Your account is locked, pay ₹99 now” (a) spam (b) not spam
- 23.📚 Good or bad for training a model: examples of every type? (a) bad for training (b) good for training
- 24.True or false: the message “You won a free phone! Click now!” should be labelled “spam”. (a) False (b) True
- 25.📚 Good or bad for training a model: testing on training data? (a) good for training (b) bad for training
- 26.True or false: “only one kind of example” is bad for training a model. (a) False (b) True
- 27.True or false: the message “Last chance! Free gift card inside” should be labelled “not spam”. (a) False (b) True
- 28.🔍 Which is the odd one out? (a) correct labels (b) testing on training data (c) photos in many lights (d) new data for testing
- 29.True or false: “examples of every type” is bad for training a model. (a) False (b) True
- 30.📚 Good or bad for training a model: many varied examples? (a) bad for training (b) good for training
- 31.True or false: “correct labels” is bad for training a model. (a) True (b) False
- 32.📚 Good or bad for training a model: labels added at random? (a) good for training (b) bad for training
- 33.📚 Good or bad for training a model: blurry, unclear photos? (a) good for training (b) bad for training
- 34.True or false: the message “You won a free phone! Click now!” should be labelled “not spam”. (a) False (b) True
- 35.True or false: “many varied examples” is good for training a model. (a) False (b) True
- 36.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Match practice moved to 5 pm” (a) spam (b) not spam
- 37.📚 Good or bad for training a model: copies of one photo? (a) bad for training (b) good for training
- 38.True or false: “checking labels twice” is good for training a model. (a) True (b) False
- 39.True or false: the message “The class picnic is on Friday at 8 am” should be labelled “not spam”. (a) False (b) True
- 40.🏷️ You are labelling messages to train a spam filter. How should this one be labelled? “Earn ₹50,000 a day from home!!!” (a) not spam (b) spam
Answer key
- it may get it wrong
- bad for training
- False
- True
- False
- testing on training data
- False
- False
- better at its task
- good for training
- examples of every type
- the right answer tag
- labels added at random
- many varied examples
- False
- new data for testing
- spam
- not spam
- False
- False
- correct labels
- spam
- good for training
- True
- bad for training
- True
- False
- testing on training data
- False
- good for training
- False
- bad for training
- bad for training
- False
- True
- not spam
- bad for training
- True
- True
- spam
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students