Build Your Own AI Project Worksheet
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.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
- 2.🧪 What is accuracy? (a) total − correct (b) correct ÷ total × 100 (c) correct + total (d) total × 2
- 3.🧪 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
- 4.📋 Planning an AI project: which comes first — train the model or label each example? (a) train the model (b) label each example
- 5.📋 Planning an AI project: which comes first — calculate percent right or split train and test? (a) calculate percent right (b) split train and test
- 6.📋 Planning an AI project: which comes first — correct bad labels or train the model? (a) correct bad labels (b) train the model
- 7.🎯 Kabir’s leaf identifier was tested on 4 new leaf photos and got 3 right. What is its accuracy in percent?
- 8.🎯 Meera’s leaf identifier was tested on 20 new leaf photos and got 12 right. What is its accuracy in percent?
- 9.📋 Planning an AI project: which comes first — improve data, retest or recheck every label? (a) improve data, retest (b) recheck every label
- 10.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
- 11.🎯 Aarav’s bird-song app is 80% accurate. If it is tested on 10 new bird songs, how many should it get right?
- 12.📦 Arjun collected 200 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 13.🧪 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
- 14.📦 Rohan collected 60 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 15.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 23 right and Model B got 20 right. How many percentage points more accurate is Model A?
- 16.📦 Ananya collected 90 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 17.📋 Planning an AI project: which comes first — train the model or choose what to sort? (a) train the model (b) choose what to sort
- 18.📋 Planning an AI project: which comes first — improve data, retest or work out the accuracy? (a) improve data, retest (b) work out the accuracy
- 19.📋 Planning an AI project: which comes first — correct bad labels or test on new photos? (a) correct bad labels (b) test on new photos
- 20.📋 Planning an AI project: which comes first — recheck every label or train the model? (a) recheck every label (b) train the model
- 21.❌ Kabir’s handwriting reader was tested on 19 new handwritten letters and got 15 right. How many did it get wrong?
- 22.⚖️ Two handwriting reader models were tested on the same 10 handwritten letters. Model A got 7 right and Model B got 5 right. How many percentage points more accurate is Model A?
- 23.📋 Planning an AI project: which comes first — test on new photos or pick a question to solve? (a) test on new photos (b) pick a question to solve
- 24.📋 Planning an AI project: which comes first — fix it and test again or calculate percent right? (a) fix it and test again (b) calculate percent right
- 25.📋 Planning an AI project: which comes first — split train and test or pick a question to solve? (a) split train and test (b) pick a question to solve
- 26.📦 Meera collected 180 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 27.🎯 Meera’s leaf identifier was tested on 50 new leaf photos and got 43 right. What is its accuracy in percent?
- 28.📦 Kabir collected 170 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 29.🎯 Tara’s fruit sorter is 50% accurate. If it is tested on 80 new fruit photos, how many should it get right?
- 30.📋 Planning an AI project: which comes first — improve data, retest or split train and test? (a) improve data, retest (b) split train and test
- 31.📋 Planning an AI project: which comes first — recheck every label or improve data, retest? (a) recheck every label (b) improve data, retest
- 32.📋 Planning an AI project: which comes first — correct bad labels or collect fruit photos? (a) correct bad labels (b) collect fruit photos
- 33.🎯 Rohan’s handwriting reader is 60% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
- 34.🎯 Vihaan’s spam spotter was tested on 4 new messages and got 4 right. What is its accuracy in percent?
- 35.📋 Planning an AI project: which comes first — let it learn patterns or calculate percent right? (a) let it learn patterns (b) calculate percent right
- 36.🧪 You can plan a simple AI project with… (a) nothing at all (b) paper and examples (c) a secret password (d) only a big robot
- 37.📋 Planning an AI project: which comes first — calculate percent right or fix it and test again? (a) calculate percent right (b) fix it and test again
- 38.📋 Planning an AI project: which comes first — label each example or gather many examples? (a) label each example (b) gather many examples
- 39.🎯 Saanvi’s bird-song app was tested on 10 new bird songs and got 5 right. What is its accuracy in percent?
- 40.📋 Planning an AI project: which comes first — let it learn patterns or pick a question to solve? (a) let it learn patterns (b) pick a question to solve
Answer key
- test on new photos
- correct ÷ total × 100
- more labelled examples
- label each example
- split train and test
- correct bad labels
- 75
- 60
- recheck every label
- train the model
- 8
- 160
- to see if it learned
- 48
- 12
- 72
- choose what to sort
- work out the accuracy
- correct bad labels
- recheck every label
- 4
- 20
- pick a question to solve
- calculate percent right
- pick a question to solve
- 144
- 86
- 136
- 40
- split train and test
- recheck every label
- collect fruit photos
- 12
- 100
- let it learn patterns
- paper and examples
- calculate percent right
- gather many examples
- 50
- pick a question to solve
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students