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.🎯 Arjun’s handwriting reader is 90% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
- 2.📦 Vihaan collected 60 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 3.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 19 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 4.📦 Ananya collected 200 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 5.📦 Kabir collected 90 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 6.📦 Rohan collected 130 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 7.📦 Vihaan collected 180 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 8.🎯 Vihaan’s bird-song app is 70% accurate. If it is tested on 60 new bird songs, how many should it get right?
- 9.❌ Arjun’s spam spotter was tested on 23 new messages and got 21 right. How many did it get wrong?
- 10.⚖️ Two leaf identifier models were tested on the same 50 leaf photos. Model A got 50 right and Model B got 48 right. How many percentage points more accurate is Model A?
- 11.🎯 Tara’s bird-song app is 60% accurate. If it is tested on 30 new bird songs, how many should it get right?
- 12.📦 Meera collected 100 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 13.📦 Ananya collected 120 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 14.🧪 You can plan a simple AI project with… (a) a secret password (b) only a big robot (c) paper and examples (d) nothing at all
- 15.📋 Planning an AI project: which comes first — test on new photos or calculate percent right? (a) test on new photos (b) calculate percent right
- 16.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to save paper (c) to make it bigger (d) to see if it learned
- 17.📋 Planning an AI project: which comes first — gather many examples or recheck every label? (a) gather many examples (b) recheck every label
- 18.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 10 right and Model B got 5 right. How many percentage points more accurate is Model A?
- 19.📋 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
- 20.📦 Saanvi collected 140 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 21.📋 Planning an AI project: which comes first — recheck every label or improve data, retest? (a) recheck every label (b) improve data, retest
- 22.⚖️ Two leaf identifier models were tested on the same 25 leaf photos. Model A got 25 right and Model B got 24 right. How many percentage points more accurate is Model A?
- 23.📋 Planning an AI project: which comes first — gather many examples or split train and test? (a) gather many examples (b) split train and test
- 24.🎯 Ananya’s handwriting reader is 50% accurate. If it is tested on 30 new handwritten letters, how many should it get right?
- 25.❌ Ishaan’s bird-song app was tested on 33 new bird songs and got 27 right. How many did it get wrong?
- 26.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
- 27.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a new colour screen (b) more labelled examples (c) a louder speaker (d) fewer examples
- 28.📋 Planning an AI project: which comes first — let it learn patterns or choose what to sort? (a) let it learn patterns (b) choose what to sort
- 29.📋 Planning an AI project: which comes first — calculate percent right or recheck every label? (a) calculate percent right (b) recheck every label
- 30.❌ Aarav’s spam spotter was tested on 35 new messages and got 33 right. How many did it get wrong?
- 31.⚖️ Two fruit sorter models were tested on the same 50 fruit photos. Model A got 48 right and Model B got 36 right. How many percentage points more accurate is Model A?
- 32.📋 Planning an AI project: which comes first — work out the accuracy or let it learn patterns? (a) work out the accuracy (b) let it learn patterns
- 33.📦 Arjun collected 100 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 34.📋 Planning an AI project: which comes first — let it learn patterns or tag each photo by type? (a) let it learn patterns (b) tag each photo by type
- 35.🎯 Meera’s bird-song app is 50% accurate. If it is tested on 30 new bird songs, how many should it get right?
- 36.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 19 right and Model B got 11 right. How many percentage points more accurate is Model A?
- 37.📋 Planning an AI project: which comes first — gather many examples or fix it and test again? (a) gather many examples (b) fix it and test again
- 38.🎯 Arjun’s handwriting reader is 70% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
- 39.📋 Planning an AI project: which comes first — tag each photo by type or calculate percent right? (a) tag each photo by type (b) calculate percent right
- 40.❌ Kabir’s leaf identifier was tested on 44 new leaf photos and got 41 right. How many did it get wrong?
Answer key
- 18
- 48
- 24
- 160
- 72
- 104
- 144
- 42
- 2
- 4
- 18
- 80
- 96
- paper and examples
- test on new photos
- to see if it learned
- gather many examples
- 50
- tag each photo by type
- 112
- recheck every label
- 4
- gather many examples
- 15
- 6
- 10
- more labelled examples
- choose what to sort
- recheck every label
- 2
- 24
- let it learn patterns
- 80
- tag each photo by type
- 15
- 40
- gather many examples
- 14
- tag each photo by type
- 3
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students