← 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 58 · 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 — try unseen examples or fix it and test again? (a) try unseen examples (b) fix it and test again
  2. 2.📋 Planning an AI project: which comes first — set aside test photos or train the model? (a) set aside test photos (b) train the model
  3. 3.📦 Ishaan collected 190 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  4. 4.🎯 Tara’s recycling sorter was tested on 5 new waste photos and got 5 right. What is its accuracy in percent?
  5. 5.🧪 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
  6. 6.📋 Planning an AI project: which comes first — train the model or split train and test? (a) train the model (b) split train and test
  7. 7.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
  8. 8.🎯 Nisha’s bird-song app is 90% accurate. If it is tested on 70 new bird songs, how many should it get right?
  9. 9.🧪 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
  10. 10.🎯 Saanvi’s recycling sorter is 90% accurate. If it is tested on 70 new waste photos, how many should it get right?
  11. 11.🎯 Vihaan’s bird-song app was tested on 10 new bird songs and got 8 right. What is its accuracy in percent?
  12. 12.🧪 What is accuracy? (a) total × 2 (b) correct ÷ total × 100 (c) total − correct (d) correct + total
  13. 13.📋 Planning an AI project: which comes first — tag each photo by type or gather many examples? (a) tag each photo by type (b) gather many examples
  14. 14.🎯 Vihaan’s bird-song app was tested on 10 new bird songs and got 9 right. What is its accuracy in percent?
  15. 15.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
  16. 16.🎯 Tara’s bird-song app is 60% accurate. If it is tested on 70 new bird songs, how many should it get right?
  17. 17.⚖️ Two handwriting reader models were tested on the same 10 handwritten letters. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
  18. 18.📋 Planning an AI project: which comes first — let it learn patterns or calculate percent right? (a) let it learn patterns (b) calculate percent right
  19. 19.🎯 Kabir’s bird-song app was tested on 5 new bird songs and got 5 right. What is its accuracy in percent?
  20. 20.❌ Ananya’s bird-song app was tested on 13 new bird songs and got 11 right. How many did it get wrong?
  21. 21.🎯 Rohan’s spam spotter was tested on 4 new messages and got 3 right. What is its accuracy in percent?
  22. 22.🎯 Ishaan’s spam spotter was tested on 10 new messages and got 6 right. What is its accuracy in percent?
  23. 23.📦 Rohan collected 150 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  24. 24.📋 Planning an AI project: which comes first — calculate percent right or tag each photo by type? (a) calculate percent right (b) tag each photo by type
  25. 25.📦 Saanvi collected 170 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  26. 26.🎯 Kabir’s recycling sorter is 70% accurate. If it is tested on 20 new waste photos, how many should it get right?
  27. 27.🎯 Kabir’s fruit sorter is 50% accurate. If it is tested on 60 new fruit photos, how many should it get right?
  28. 28.⚖️ Two recycling sorter models were tested on the same 50 waste photos. Model A got 50 right and Model B got 46 right. How many percentage points more accurate is Model A?
  29. 29.🎯 Ananya’s fruit sorter is 90% accurate. If it is tested on 60 new fruit photos, how many should it get right?
  30. 30.🎯 Arjun’s spam spotter is 50% accurate. If it is tested on 20 new messages, how many should it get right?
  31. 31.🧪 You can plan a simple AI project with… (a) a secret password (b) only a big robot (c) nothing at all (d) paper and examples
  32. 32.📦 Ananya collected 150 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  33. 33.📋 Planning an AI project: which comes first — train the model or calculate percent right? (a) train the model (b) calculate percent right
  34. 34.📦 Kabir collected 120 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  35. 35.📋 Planning an AI project: which comes first — work out the accuracy or improve data, retest? (a) work out the accuracy (b) improve data, retest
  36. 36.📋 Planning an AI project: which comes first — correct bad labels or calculate percent right? (a) correct bad labels (b) calculate percent right
  37. 37.📋 Planning an AI project: which comes first — let it learn patterns or improve data, retest? (a) let it learn patterns (b) improve data, retest
  38. 38.🎯 Ishaan’s handwriting reader is 80% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
  39. 39.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 10 right and Model B got 7 right. How many percentage points more accurate is Model A?
  40. 40.📋 Planning an AI project: which comes first — test on new photos or train the model? (a) test on new photos (b) train the model

Answer key

  1. try unseen examples
  2. set aside test photos
  3. 152
  4. 100
  5. to see if it learned
  6. split train and test
  7. calculate percent right
  8. 63
  9. more labelled examples
  10. 63
  11. 80
  12. correct ÷ total × 100
  13. gather many examples
  14. 90
  15. 10
  16. 42
  17. 10
  18. let it learn patterns
  19. 100
  20. 2
  21. 75
  22. 60
  23. 120
  24. tag each photo by type
  25. 136
  26. 14
  27. 30
  28. 8
  29. 54
  30. 10
  31. paper and examples
  32. 120
  33. train the model
  34. 96
  35. work out the accuracy
  36. correct bad labels
  37. let it learn patterns
  38. 16
  39. 30
  40. train the model

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