← 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 691 · 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 save paper (b) to see if it learned (c) to make it faster (d) to make it bigger
  2. 2.❌ Aarav’s leaf identifier was tested on 21 new leaf photos and got 12 right. How many did it get wrong?
  3. 3.🎯 Tara’s leaf identifier is 70% accurate. If it is tested on 50 new leaf photos, how many should it get right?
  4. 4.📋 Planning an AI project: which comes first — label each example or calculate percent right? (a) label each example (b) calculate percent right
  5. 5.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 20 right and Model B got 19 right. How many percentage points more accurate is Model A?
  6. 6.📋 Planning an AI project: which comes first — label each example or correct bad labels? (a) label each example (b) correct bad labels
  7. 7.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a new colour screen (b) a louder speaker (c) fewer examples (d) more labelled examples
  8. 8.📋 Planning an AI project: which comes first — train the model or choose what to sort? (a) train the model (b) choose what to sort
  9. 9.📋 Planning an AI project: which comes first — pick a question to solve or work out the accuracy? (a) pick a question to solve (b) work out the accuracy
  10. 10.📋 Planning an AI project: which comes first — train the model or test on new photos? (a) train the model (b) test on new photos
  11. 11.🧪 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
  12. 12.🎯 Kabir’s handwriting reader is 90% accurate. If it is tested on 70 new handwritten letters, how many should it get right?
  13. 13.❌ Rohan’s recycling sorter was tested on 35 new waste photos and got 26 right. How many did it get wrong?
  14. 14.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 6 right and Model B got 5 right. How many percentage points more accurate is Model A?
  15. 15.📋 Planning an AI project: which comes first — label each example or improve data, retest? (a) label each example (b) improve data, retest
  16. 16.📦 Saanvi collected 150 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
  17. 17.🧪 What is accuracy? (a) correct ÷ total × 100 (b) correct + total (c) total × 2 (d) total − correct
  18. 18.📋 Planning an AI project: which comes first — pick a question to solve or recheck every label? (a) pick a question to solve (b) recheck every label
  19. 19.📋 Planning an AI project: which comes first — correct bad labels or set aside test photos? (a) correct bad labels (b) set aside test photos
  20. 20.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 9 right and Model B got 5 right. How many percentage points more accurate is Model A?
  21. 21.🎯 Ananya’s leaf identifier was tested on 50 new leaf photos and got 38 right. What is its accuracy in percent?
  22. 22.📋 Planning an AI project: which comes first — choose what to sort or train the model? (a) choose what to sort (b) train the model
  23. 23.📋 Planning an AI project: which comes first — correct bad labels or improve data, retest? (a) correct bad labels (b) improve data, retest
  24. 24.📦 Ananya collected 50 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
  25. 25.❌ Ananya’s handwriting reader was tested on 17 new handwritten letters and got 16 right. How many did it get wrong?
  26. 26.📋 Planning an AI project: which comes first — split train and test or improve data, retest? (a) split train and test (b) improve data, retest
  27. 27.📋 Planning an AI project: which comes first — calculate percent right or let it learn patterns? (a) calculate percent right (b) let it learn patterns
  28. 28.🎯 Nisha’s bird-song app is 90% accurate. If it is tested on 30 new bird songs, how many should it get right?
  29. 29.🎯 Saanvi’s recycling sorter is 50% accurate. If it is tested on 100 new waste photos, how many should it get right?
  30. 30.❌ Aarav’s handwriting reader was tested on 20 new handwritten letters and got 18 right. How many did it get wrong?
  31. 31.📋 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
  32. 32.📦 Vihaan collected 40 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
  33. 33.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 19 right and Model B got 15 right. How many percentage points more accurate is Model A?
  34. 34.🎯 Kabir’s handwriting reader was tested on 5 new handwritten letters and got 4 right. What is its accuracy in percent?
  35. 35.📦 Meera collected 160 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
  36. 36.📋 Planning an AI project: which comes first — collect fruit photos or choose what to sort? (a) collect fruit photos (b) choose what to sort
  37. 37.🎯 Vihaan’s recycling sorter was tested on 25 new waste photos and got 21 right. What is its accuracy in percent?
  38. 38.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 22 right and Model B got 20 right. How many percentage points more accurate is Model A?
  39. 39.🎯 Tara’s bird-song app is 50% accurate. If it is tested on 50 new bird songs, how many should it get right?
  40. 40.❌ Diya’s recycling sorter was tested on 50 new waste photos and got 44 right. How many did it get wrong?

Answer key

  1. to see if it learned
  2. 9
  3. 35
  4. label each example
  5. 5
  6. label each example
  7. more labelled examples
  8. choose what to sort
  9. pick a question to solve
  10. train the model
  11. paper and examples
  12. 63
  13. 9
  14. 10
  15. label each example
  16. 120
  17. correct ÷ total × 100
  18. pick a question to solve
  19. correct bad labels
  20. 40
  21. 76
  22. choose what to sort
  23. correct bad labels
  24. 40
  25. 1
  26. split train and test
  27. let it learn patterns
  28. 27
  29. 50
  30. 2
  31. tag each photo by type
  32. 32
  33. 20
  34. 80
  35. 128
  36. choose what to sort
  37. 84
  38. 8
  39. 25
  40. 6

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