← 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 877 · 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.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to make it faster (c) to save paper (d) to see if it learned
  2. 2.📋 Planning an AI project: which comes first — let it learn patterns or split train and test? (a) let it learn patterns (b) split train and test
  3. 3.📋 Planning an AI project: which comes first — work out the accuracy or split train and test? (a) work out the accuracy (b) split train and test
  4. 4.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 10 right and Model B got 6 right. How many percentage points more accurate is Model A?
  5. 5.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) more labelled examples (c) fewer examples (d) a new colour screen
  6. 6.📋 Planning an AI project: which comes first — correct bad labels or collect fruit photos? (a) correct bad labels (b) collect fruit photos
  7. 7.🧪 What is accuracy? (a) correct + total (b) correct ÷ total × 100 (c) total × 2 (d) total − correct
  8. 8.📋 Planning an AI project: which comes first — choose what to sort or work out the accuracy? (a) choose what to sort (b) work out the accuracy
  9. 9.📋 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
  10. 10.⚖️ Two handwriting reader models were tested on the same 20 handwritten letters. Model A got 18 right and Model B got 16 right. How many percentage points more accurate is Model A?
  11. 11.📦 Aarav collected 130 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  12. 12.🎯 Vihaan’s recycling sorter was tested on 5 new waste photos and got 5 right. What is its accuracy in percent?
  13. 13.🧪 You can plan a simple AI project with… (a) paper and examples (b) a secret password (c) nothing at all (d) only a big robot
  14. 14.📦 Diya collected 140 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  15. 15.📋 Planning an AI project: which comes first — improve data, retest or tag each photo by type? (a) improve data, retest (b) tag each photo by type
  16. 16.🎯 Diya’s handwriting reader is 70% accurate. If it is tested on 80 new handwritten letters, how many should it get right?
  17. 17.📋 Planning an AI project: which comes first — calculate percent right or let it learn patterns? (a) calculate percent right (b) let it learn patterns
  18. 18.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 35 right and Model B got 26 right. How many percentage points more accurate is Model A?
  19. 19.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 8 right and Model B got 6 right. How many percentage points more accurate is Model A?
  20. 20.🎯 Aarav’s spam spotter was tested on 4 new messages and got 4 right. What is its accuracy in percent?
  21. 21.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 22 right and Model B got 20 right. How many percentage points more accurate is Model A?
  22. 22.📋 Planning an AI project: which comes first — fix it and test again or choose what to sort? (a) fix it and test again (b) choose what to sort
  23. 23.📋 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
  24. 24.🎯 Nisha’s recycling sorter is 50% accurate. If it is tested on 40 new waste photos, how many should it get right?
  25. 25.📋 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
  26. 26.📦 Kabir collected 90 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  27. 27.📦 Ishaan collected 50 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  28. 28.🎯 Arjun’s leaf identifier is 50% accurate. If it is tested on 70 new leaf photos, how many should it get right?
  29. 29.📋 Planning an AI project: which comes first — train the model or try unseen examples? (a) train the model (b) try unseen examples
  30. 30.📦 Arjun collected 100 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  31. 31.📋 Planning an AI project: which comes first — calculate percent right or test on new photos? (a) calculate percent right (b) test on new photos
  32. 32.📋 Planning an AI project: which comes first — set aside test photos or label each example? (a) set aside test photos (b) label each example
  33. 33.🎯 Meera’s handwriting reader was tested on 50 new handwritten letters and got 34 right. What is its accuracy in percent?
  34. 34.🎯 Ananya’s leaf identifier is 50% accurate. If it is tested on 60 new leaf photos, how many should it get right?
  35. 35.📋 Planning an AI project: which comes first — test on new photos or label each example? (a) test on new photos (b) label each example
  36. 36.📦 Meera collected 180 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  37. 37.📦 Rohan collected 60 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  38. 38.🎯 Saanvi’s handwriting reader is 90% accurate. If it is tested on 60 new handwritten letters, how many should it get right?
  39. 39.🎯 Arjun’s spam spotter was tested on 25 new messages and got 18 right. What is its accuracy in percent?
  40. 40.📦 Saanvi collected 80 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?

Answer key

  1. to see if it learned
  2. split train and test
  3. split train and test
  4. 40
  5. more labelled examples
  6. collect fruit photos
  7. correct ÷ total × 100
  8. choose what to sort
  9. try unseen examples
  10. 10
  11. 104
  12. 100
  13. paper and examples
  14. 112
  15. tag each photo by type
  16. 56
  17. let it learn patterns
  18. 18
  19. 20
  20. 100
  21. 8
  22. choose what to sort
  23. tag each photo by type
  24. 20
  25. tag each photo by type
  26. 72
  27. 40
  28. 35
  29. train the model
  30. 80
  31. test on new photos
  32. label each example
  33. 68
  34. 30
  35. label each example
  36. 144
  37. 48
  38. 54
  39. 72
  40. 64

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