Build Your Own AI Project Worksheet
AI tip (Accuracy = correct ÷ total × 100): Steps: 1 choose a problem → 2 collect examples → 3 label them → 4 check and correct bad labels (clean the data) → 5 split into training and test sets → 6 train → 7 test with new examples → 8 measure accuracy → 9 improve the data and retest. Accuracy = correct ÷ total × 100. Wrong = total − correct. Expected right = accuracy ÷ 100 × total. Keep some examples apart for testing (for example one fifth); the rest are for training.
NameDateTime takenScore ___ / 40
- 1.🧪 Why must you test a model on examples it has NOT seen? (a) to save paper (b) to make it bigger (c) to see if it learned (d) to make it faster
- 2.📦 Rohan collected 190 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 3.⚖️ Two recycling sorter models were tested on the same 50 waste photos. Model A got 41 right and Model B got 32 right. How many percentage points more accurate is Model A?
- 4.📋 Planning an AI project: which comes first — split train and test or correct bad labels? (a) split train and test (b) correct bad labels
- 5.❌ Kabir’s fruit sorter was tested on 19 new fruit photos and got 11 right. How many did it get wrong?
- 6.❌ Arjun’s recycling sorter was tested on 37 new waste photos and got 36 right. How many did it get wrong?
- 7.❌ Ananya’s fruit sorter was tested on 32 new fruit photos and got 31 right. How many did it get wrong?
- 8.📋 Planning an AI project: which comes first — label each example or test on new photos? (a) label each example (b) test on new photos
- 9.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
- 10.🎯 Nisha’s recycling sorter was tested on 4 new waste photos and got 4 right. What is its accuracy in percent?
- 11.🎯 Ananya’s recycling sorter was tested on 10 new waste photos and got 5 right. What is its accuracy in percent?
- 12.📦 Rohan collected 60 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 13.📋 Planning an AI project: which comes first — train the model or test on new photos? (a) train the model (b) test on new photos
- 14.⚖️ Two fruit sorter models were tested on the same 50 fruit photos. Model A got 36 right and Model B got 34 right. How many percentage points more accurate is Model A?
- 15.📋 Planning an AI project: which comes first — set aside test photos or correct bad labels? (a) set aside test photos (b) correct bad labels
- 16.📋 Planning an AI project: which comes first — collect fruit photos or choose what to sort? (a) collect fruit photos (b) choose what to sort
- 17.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a new colour screen (b) more labelled examples (c) a louder speaker (d) fewer examples
- 18.⚖️ Two bird-song app models were tested on the same 20 bird songs. Model A got 18 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 19.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 19 right and Model B got 17 right. How many percentage points more accurate is Model A?
- 20.🧪 What is accuracy? (a) correct + total (b) total − correct (c) total × 2 (d) correct ÷ total × 100
- 21.📋 Planning an AI project: which comes first — calculate percent right or improve data, retest? (a) calculate percent right (b) improve data, retest
- 22.📋 Planning an AI project: which comes first — work out the accuracy or correct bad labels? (a) work out the accuracy (b) correct bad labels
- 23.📦 Ananya collected 130 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 24.📋 Planning an AI project: which comes first — label each example or split train and test? (a) label each example (b) split train and test
- 25.❌ Saanvi’s spam spotter was tested on 22 new messages and got 21 right. How many did it get wrong?
- 26.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 17 right and Model B got 12 right. How many percentage points more accurate is Model A?
- 27.🎯 Ananya’s handwriting reader was tested on 50 new handwritten letters and got 26 right. What is its accuracy in percent?
- 28.🎯 Ananya’s handwriting reader is 80% accurate. If it is tested on 100 new handwritten letters, how many should it get right?
- 29.📦 Tara collected 90 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 30.📋 Planning an AI project: which comes first — fix it and test again or tag each photo by type? (a) fix it and test again (b) tag each photo by type
- 31.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 16 right and Model B got 15 right. How many percentage points more accurate is Model A?
- 32.🎯 Aarav’s recycling sorter was tested on 5 new waste photos and got 4 right. What is its accuracy in percent?
- 33.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 17 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 34.❌ Rohan’s recycling sorter was tested on 50 new waste photos and got 43 right. How many did it get wrong?
- 35.📋 Planning an AI project: which comes first — train the model or improve data, retest? (a) train the model (b) improve data, retest
- 36.🧪 You can plan a simple AI project with… (a) nothing at all (b) only a big robot (c) paper and examples (d) a secret password
- 37.📋 Planning an AI project: which comes first — train the model or fix it and test again? (a) train the model (b) fix it and test again
- 38.📋 Planning an AI project: which comes first — recheck every label or gather many examples? (a) recheck every label (b) gather many examples
- 39.🎯 Arjun’s spam spotter was tested on 20 new messages and got 19 right. What is its accuracy in percent?
- 40.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 25 right and Model B got 24 right. How many percentage points more accurate is Model A?
Answer key
- to see if it learned
- 152
- 18
- correct bad labels
- 8
- 1
- 1
- label each example
- test on new photos
- 100
- 50
- 48
- train the model
- 4
- correct bad labels
- choose what to sort
- more labelled examples
- 25
- 10
- correct ÷ total × 100
- calculate percent right
- correct bad labels
- 104
- label each example
- 1
- 25
- 52
- 80
- 72
- tag each photo by type
- 5
- 80
- 16
- 7
- train the model
- paper and examples
- train the model
- gather many examples
- 95
- 4
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students