← 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 916 · 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.🎯 Rohan’s handwriting reader is 50% accurate. If it is tested on 90 new handwritten letters, how many should it get right?
  2. 2.⚖️ Two recycling sorter models were tested on the same 50 waste photos. Model A got 48 right and Model B got 42 right. How many percentage points more accurate is Model A?
  3. 3.🧪 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
  4. 4.❌ Saanvi’s leaf identifier was tested on 32 new leaf photos and got 24 right. How many did it get wrong?
  5. 5.📋 Planning an AI project: which comes first — split train and test or choose what to sort? (a) split train and test (b) choose what to sort
  6. 6.📦 Aarav collected 90 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  7. 7.🎯 Aarav’s handwriting reader was tested on 20 new handwritten letters and got 11 right. What is its accuracy in percent?
  8. 8.🧪 You can plan a simple AI project with… (a) paper and examples (b) a secret password (c) only a big robot (d) nothing at all
  9. 9.📋 Planning an AI project: which comes first — try unseen examples or split train and test? (a) try unseen examples (b) split train and test
  10. 10.📋 Planning an AI project: which comes first — collect fruit photos or label each example? (a) collect fruit photos (b) label each example
  11. 11.📦 Rohan collected 120 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  12. 12.🧪 What is accuracy? (a) correct + total (b) total × 2 (c) correct ÷ total × 100 (d) total − correct
  13. 13.📦 Meera collected 60 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  14. 14.📋 Planning an AI project: which comes first — set aside test photos or label each example? (a) set aside test photos (b) label each example
  15. 15.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 25 right and Model B got 16 right. How many percentage points more accurate is Model A?
  16. 16.🧪 Why must you test a model on examples it has NOT seen? (a) to save paper (b) to make it bigger (c) to see if it learned (d) to make it faster
  17. 17.🎯 Nisha’s handwriting reader is 90% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
  18. 18.🎯 Meera’s fruit sorter was tested on 20 new fruit photos and got 18 right. What is its accuracy in percent?
  19. 19.🎯 Aarav’s spam spotter was tested on 50 new messages and got 27 right. What is its accuracy in percent?
  20. 20.📋 Planning an AI project: which comes first — let it learn patterns or improve data, retest? (a) let it learn patterns (b) improve data, retest
  21. 21.📦 Diya collected 40 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  22. 22.⚖️ 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?
  23. 23.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
  24. 24.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 8 right and Model B got 7 right. How many percentage points more accurate is Model A?
  25. 25.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 19 right and Model B got 17 right. How many percentage points more accurate is Model A?
  26. 26.📋 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
  27. 27.🎯 Diya’s fruit sorter was tested on 4 new fruit photos and got 4 right. What is its accuracy in percent?
  28. 28.📦 Ishaan collected 190 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
  29. 29.❌ Rohan’s fruit sorter was tested on 25 new fruit photos and got 24 right. How many did it get wrong?
  30. 30.❌ Rohan’s leaf identifier was tested on 50 new leaf photos and got 42 right. How many did it get wrong?
  31. 31.🎯 Nisha’s bird-song app is 60% accurate. If it is tested on 10 new bird songs, how many should it get right?
  32. 32.🎯 Tara’s fruit sorter is 60% accurate. If it is tested on 80 new fruit photos, how many should it get right?
  33. 33.📦 Tara collected 40 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  34. 34.📋 Planning an AI project: which comes first — train the model or correct bad labels? (a) train the model (b) correct bad labels
  35. 35.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 20 right and Model B got 16 right. How many percentage points more accurate is Model A?
  36. 36.📋 Planning an AI project: which comes first — tag each photo by type or recheck every label? (a) tag each photo by type (b) recheck every label
  37. 37.❌ Aarav’s leaf identifier was tested on 20 new leaf photos and got 14 right. How many did it get wrong?
  38. 38.📦 Aarav collected 50 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
  39. 39.❌ Tara’s recycling sorter was tested on 50 new waste photos and got 45 right. How many did it get wrong?
  40. 40.🎯 Rohan’s spam spotter was tested on 50 new messages and got 42 right. What is its accuracy in percent?

Answer key

  1. 45
  2. 12
  3. more labelled examples
  4. 8
  5. choose what to sort
  6. 72
  7. 55
  8. paper and examples
  9. split train and test
  10. collect fruit photos
  11. 96
  12. correct ÷ total × 100
  13. 48
  14. label each example
  15. 36
  16. to see if it learned
  17. 18
  18. 90
  19. 54
  20. let it learn patterns
  21. 32
  22. 4
  23. 10
  24. 10
  25. 8
  26. pick a question to solve
  27. 100
  28. 152
  29. 1
  30. 8
  31. 6
  32. 48
  33. 32
  34. correct bad labels
  35. 20
  36. tag each photo by type
  37. 6
  38. 40
  39. 5
  40. 84

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