← 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 730 · 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.📋 Planning an AI project: which comes first — fix it and test again or set aside test photos? (a) fix it and test again (b) set aside test photos
  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.❌ Saanvi’s handwriting reader was tested on 21 new handwritten letters and got 16 right. How many did it get wrong?
  4. 4.📦 Tara collected 130 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  5. 5.📋 Planning an AI project: which comes first — work out the accuracy or correct bad labels? (a) work out the accuracy (b) correct bad labels
  6. 6.🎯 Kabir’s handwriting reader was tested on 20 new handwritten letters and got 12 right. What is its accuracy in percent?
  7. 7.📋 Planning an AI project: which comes first — tag each photo by type or fix it and test again? (a) tag each photo by type (b) fix it and test again
  8. 8.🎯 Meera’s leaf identifier is 80% accurate. If it is tested on 10 new leaf photos, how many should it get right?
  9. 9.🧪 What is accuracy? (a) correct ÷ total × 100 (b) total × 2 (c) correct + total (d) total − correct
  10. 10.📦 Kabir collected 50 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  11. 11.❌ Saanvi’s bird-song app was tested on 24 new bird songs and got 20 right. How many did it get wrong?
  12. 12.📦 Meera collected 100 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  13. 13.❌ Arjun’s recycling sorter was tested on 19 new waste photos and got 16 right. How many did it get wrong?
  14. 14.❌ Tara’s fruit sorter was tested on 21 new fruit photos and got 15 right. How many did it get wrong?
  15. 15.📋 Planning an AI project: which comes first — let it learn patterns or fix it and test again? (a) let it learn patterns (b) fix it and test again
  16. 16.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
  17. 17.📋 Planning an AI project: which comes first — tag each photo by type or pick a question to solve? (a) tag each photo by type (b) pick a question to solve
  18. 18.📋 Planning an AI project: which comes first — pick a question to solve or set aside test photos? (a) pick a question to solve (b) set aside test photos
  19. 19.📋 Planning an AI project: which comes first — let it learn patterns or test on new photos? (a) let it learn patterns (b) test on new photos
  20. 20.📋 Planning an AI project: which comes first — train the model or label each example? (a) train the model (b) label each example
  21. 21.📋 Planning an AI project: which comes first — calculate percent right or try unseen examples? (a) calculate percent right (b) try unseen examples
  22. 22.📋 Planning an AI project: which comes first — choose what to sort or fix it and test again? (a) choose what to sort (b) fix it and test again
  23. 23.📦 Saanvi collected 120 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  24. 24.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) a louder speaker (c) a new colour screen (d) fewer examples
  25. 25.🎯 Diya’s fruit sorter is 80% accurate. If it is tested on 30 new fruit photos, how many should it get right?
  26. 26.🎯 Kabir’s bird-song app was tested on 50 new bird songs and got 25 right. What is its accuracy in percent?
  27. 27.📋 Planning an AI project: which comes first — work out the accuracy or fix it and test again? (a) work out the accuracy (b) fix it and test again
  28. 28.❌ Meera’s leaf identifier was tested on 50 new leaf photos and got 42 right. How many did it get wrong?
  29. 29.🎯 Ananya’s leaf identifier is 70% accurate. If it is tested on 60 new leaf photos, how many should it get right?
  30. 30.🎯 Meera’s spam spotter is 50% accurate. If it is tested on 50 new messages, how many should it get right?
  31. 31.📋 Planning an AI project: which comes first — collect fruit photos or tag each photo by type? (a) collect fruit photos (b) tag each photo by type
  32. 32.📋 Planning an AI project: which comes first — correct bad labels or improve data, retest? (a) correct bad labels (b) improve data, retest
  33. 33.📦 Diya collected 180 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  34. 34.📋 Planning an AI project: which comes first — correct bad labels or collect fruit photos? (a) correct bad labels (b) collect fruit photos
  35. 35.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to save paper (c) to see if it learned (d) to make it bigger
  36. 36.📋 Planning an AI project: which comes first — choose what to sort or improve data, retest? (a) choose what to sort (b) improve data, retest
  37. 37.📋 Planning an AI project: which comes first — choose what to sort or set aside test photos? (a) choose what to sort (b) set aside test photos
  38. 38.📋 Planning an AI project: which comes first — set aside test photos or improve data, retest? (a) set aside test photos (b) improve data, retest
  39. 39.📋 Planning an AI project: which comes first — recheck every label or let it learn patterns? (a) recheck every label (b) let it learn patterns
  40. 40.🎯 Saanvi’s recycling sorter is 50% accurate. If it is tested on 90 new waste photos, how many should it get right?

Answer key

  1. set aside test photos
  2. tag each photo by type
  3. 5
  4. 104
  5. correct bad labels
  6. 60
  7. tag each photo by type
  8. 8
  9. correct ÷ total × 100
  10. 40
  11. 4
  12. 80
  13. 3
  14. 6
  15. let it learn patterns
  16. test on new photos
  17. pick a question to solve
  18. pick a question to solve
  19. let it learn patterns
  20. label each example
  21. try unseen examples
  22. choose what to sort
  23. 96
  24. more labelled examples
  25. 24
  26. 50
  27. work out the accuracy
  28. 8
  29. 42
  30. 25
  31. collect fruit photos
  32. correct bad labels
  33. 144
  34. collect fruit photos
  35. to see if it learned
  36. choose what to sort
  37. choose what to sort
  38. set aside test photos
  39. recheck every label
  40. 45

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