← 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 19 · 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.❌ Tara’s spam spotter was tested on 50 new messages and got 49 right. How many did it get wrong?
  2. 2.📋 Planning an AI project: which comes first — tag each photo by type or work out the accuracy? (a) tag each photo by type (b) work out the accuracy
  3. 3.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 17 right and Model B got 15 right. How many percentage points more accurate is Model A?
  4. 4.❌ Tara’s recycling sorter was tested on 49 new waste photos and got 45 right. How many did it get wrong?
  5. 5.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 13 right and Model B got 11 right. How many percentage points more accurate is Model A?
  6. 6.📋 Planning an AI project: which comes first — pick a question to solve or tag each photo by type? (a) pick a question to solve (b) tag each photo by type
  7. 7.❌ Ananya’s spam spotter was tested on 43 new messages and got 41 right. How many did it get wrong?
  8. 8.📋 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
  9. 9.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
  10. 10.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 8 right and Model B got 5 right. How many percentage points more accurate is Model A?
  11. 11.📋 Planning an AI project: which comes first — label each example or improve data, retest? (a) label each example (b) improve data, retest
  12. 12.🎯 Ananya’s fruit sorter was tested on 4 new fruit photos and got 2 right. What is its accuracy in percent?
  13. 13.🎯 Meera’s leaf identifier is 50% accurate. If it is tested on 100 new leaf photos, how many should it get right?
  14. 14.❌ Nisha’s handwriting reader was tested on 14 new handwritten letters and got 11 right. How many did it get wrong?
  15. 15.📋 Planning an AI project: which comes first — try unseen examples or work out the accuracy? (a) try unseen examples (b) work out the accuracy
  16. 16.📋 Planning an AI project: which comes first — tag each photo by type or correct bad labels? (a) tag each photo by type (b) correct bad labels
  17. 17.🧪 You can plan a simple AI project with… (a) only a big robot (b) paper and examples (c) nothing at all (d) a secret password
  18. 18.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) a new colour screen (c) fewer examples (d) a louder speaker
  19. 19.📋 Planning an AI project: which comes first — gather many examples or work out the accuracy? (a) gather many examples (b) work out the accuracy
  20. 20.📋 Planning an AI project: which comes first — calculate percent right or gather many examples? (a) calculate percent right (b) gather many examples
  21. 21.📋 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
  22. 22.📦 Aarav collected 170 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  23. 23.🎯 Ananya’s handwriting reader was tested on 25 new handwritten letters and got 18 right. What is its accuracy in percent?
  24. 24.📋 Planning an AI project: which comes first — test on new photos or correct bad labels? (a) test on new photos (b) correct bad labels
  25. 25.📦 Saanvi collected 190 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  26. 26.🎯 Saanvi’s leaf identifier was tested on 20 new leaf photos and got 19 right. What is its accuracy in percent?
  27. 27.📋 Planning an AI project: which comes first — split train and test or let it learn patterns? (a) split train and test (b) let it learn patterns
  28. 28.📦 Arjun collected 170 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  29. 29.🧪 What is accuracy? (a) correct + total (b) total × 2 (c) correct ÷ total × 100 (d) total − correct
  30. 30.❌ Rohan’s bird-song app was tested on 30 new bird songs and got 28 right. How many did it get wrong?
  31. 31.❌ Tara’s recycling sorter was tested on 24 new waste photos and got 19 right. How many did it get wrong?
  32. 32.🎯 Aarav’s spam spotter is 70% accurate. If it is tested on 100 new messages, how many should it get right?
  33. 33.📋 Planning an AI project: which comes first — improve data, retest or correct bad labels? (a) improve data, retest (b) correct bad labels
  34. 34.❌ Kabir’s bird-song app was tested on 33 new bird songs and got 29 right. How many did it get wrong?
  35. 35.📋 Planning an AI project: which comes first — recheck every label or choose what to sort? (a) recheck every label (b) choose what to sort
  36. 36.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 10 right and Model B got 8 right. How many percentage points more accurate is Model A?
  37. 37.📋 Planning an AI project: which comes first — correct bad labels or set aside test photos? (a) correct bad labels (b) set aside test photos
  38. 38.📋 Planning an AI project: which comes first — pick a question to solve or label each example? (a) pick a question to solve (b) label each example
  39. 39.🎯 Nisha’s recycling sorter is 90% accurate. If it is tested on 50 new waste photos, how many should it get right?
  40. 40.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 23 right and Model B got 22 right. How many percentage points more accurate is Model A?

Answer key

  1. 1
  2. tag each photo by type
  3. 10
  4. 4
  5. 10
  6. pick a question to solve
  7. 2
  8. choose what to sort
  9. calculate percent right
  10. 30
  11. label each example
  12. 50
  13. 50
  14. 3
  15. try unseen examples
  16. tag each photo by type
  17. paper and examples
  18. more labelled examples
  19. gather many examples
  20. gather many examples
  21. pick a question to solve
  22. 136
  23. 72
  24. correct bad labels
  25. 152
  26. 95
  27. split train and test
  28. 136
  29. correct ÷ total × 100
  30. 2
  31. 5
  32. 70
  33. correct bad labels
  34. 4
  35. choose what to sort
  36. 20
  37. correct bad labels
  38. pick a question to solve
  39. 45
  40. 4

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