← Design a tiny AI project lesson New set →

Build Your Own AI Project Worksheet

AI for students lesson 23: Design a tiny AI project · Set 768 · 40 questions
TalentJR

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. 1.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 8 right and Model B got 7 right. How many percentage points more accurate is Model A?
  2. 2.⚖️ Two recycling sorter models were tested on the same 25 waste photos. Model A got 22 right and Model B got 13 right. How many percentage points more accurate is Model A?
  3. 3.🎯 Diya’s recycling sorter was tested on 50 new waste photos and got 43 right. What is its accuracy in percent?
  4. 4.📦 Diya collected 90 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  5. 5.🎯 Diya’s recycling sorter is 90% accurate. If it is tested on 10 new waste photos, how many should it get right?
  6. 6.📋 Planning an AI project: which comes first — correct bad labels or set aside test photos? (a) correct bad labels (b) set aside test photos
  7. 7.⚖️ Two bird-song app models were tested on the same 20 bird songs. Model A got 13 right and Model B got 10 right. How many percentage points more accurate is Model A?
  8. 8.📋 Planning an AI project: which comes first — recheck every label or split train and test? (a) recheck every label (b) split train and test
  9. 9.❌ Aarav’s spam spotter was tested on 28 new messages and got 25 right. How many did it get wrong?
  10. 10.📋 Planning an AI project: which comes first — work out the accuracy or set aside test photos? (a) work out the accuracy (b) set aside test photos
  11. 11.🎯 Kabir’s handwriting reader is 60% accurate. If it is tested on 60 new handwritten letters, how many should it get right?
  12. 12.📦 Nisha collected 60 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  13. 13.🎯 Kabir’s handwriting reader is 80% accurate. If it is tested on 100 new handwritten letters, how many should it get right?
  14. 14.🎯 Diya’s bird-song app was tested on 5 new bird songs and got 3 right. What is its accuracy in percent?
  15. 15.🎯 Saanvi’s fruit sorter was tested on 4 new fruit photos and got 4 right. What is its accuracy in percent?
  16. 16.🧪 What is accuracy? (a) total − correct (b) correct ÷ total × 100 (c) total × 2 (d) correct + total
  17. 17.🧪 You can plan a simple AI project with… (a) nothing at all (b) a secret password (c) paper and examples (d) only a big robot
  18. 18.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) a louder speaker (c) fewer examples (d) a new colour screen
  19. 19.❌ Kabir’s recycling sorter was tested on 20 new waste photos and got 19 right. How many did it get wrong?
  20. 20.📦 Arjun collected 160 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  21. 21.📋 Planning an AI project: which comes first — correct bad labels or choose what to sort? (a) correct bad labels (b) choose what to sort
  22. 22.❌ Nisha’s bird-song app was tested on 24 new bird songs and got 22 right. How many did it get wrong?
  23. 23.🎯 Arjun’s spam spotter was tested on 4 new messages and got 3 right. What is its accuracy in percent?
  24. 24.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
  25. 25.🎯 Aarav’s fruit sorter was tested on 20 new fruit photos and got 20 right. What is its accuracy in percent?
  26. 26.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 16 right and Model B got 12 right. How many percentage points more accurate is Model A?
  27. 27.📦 Aarav collected 150 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  28. 28.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to see if it learned (c) to save paper (d) to make it faster
  29. 29.🎯 Kabir’s bird-song app was tested on 10 new bird songs and got 5 right. What is its accuracy in percent?
  30. 30.🎯 Tara’s spam spotter was tested on 50 new messages and got 40 right. What is its accuracy in percent?
  31. 31.❌ Vihaan’s spam spotter was tested on 19 new messages and got 10 right. How many did it get wrong?
  32. 32.⚖️ Two bird-song app models were tested on the same 20 bird songs. Model A got 17 right and Model B got 12 right. How many percentage points more accurate is Model A?
  33. 33.📋 Planning an AI project: which comes first — correct bad labels or try unseen examples? (a) correct bad labels (b) try unseen examples
  34. 34.📋 Planning an AI project: which comes first — choose what to sort or split train and test? (a) choose what to sort (b) split train and test
  35. 35.📋 Planning an AI project: which comes first — train the model or pick a question to solve? (a) train the model (b) pick a question to solve
  36. 36.🎯 Aarav’s recycling sorter is 90% accurate. If it is tested on 10 new waste photos, how many should it get right?
  37. 37.📋 Planning an AI project: which comes first — choose what to sort or gather many examples? (a) choose what to sort (b) gather many examples
  38. 38.🎯 Aarav’s handwriting reader was tested on 4 new handwritten letters and got 4 right. What is its accuracy in percent?
  39. 39.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 20 right and Model B got 19 right. How many percentage points more accurate is Model A?
  40. 40.📋 Planning an AI project: which comes first — calculate percent right or fix it and test again? (a) calculate percent right (b) fix it and test again

Answer key

  1. 10
  2. 36
  3. 86
  4. 72
  5. 9
  6. correct bad labels
  7. 15
  8. recheck every label
  9. 3
  10. set aside test photos
  11. 36
  12. 48
  13. 80
  14. 60
  15. 100
  16. correct ÷ total × 100
  17. paper and examples
  18. more labelled examples
  19. 1
  20. 128
  21. choose what to sort
  22. 2
  23. 75
  24. calculate percent right
  25. 100
  26. 20
  27. 120
  28. to see if it learned
  29. 50
  30. 80
  31. 9
  32. 25
  33. correct bad labels
  34. choose what to sort
  35. pick a question to solve
  36. 9
  37. choose what to sort
  38. 100
  39. 5
  40. calculate percent right

Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students