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.🎯 Vihaan’s leaf identifier is 50% accurate. If it is tested on 50 new leaf photos, how many should it get right?
- 2.🎯 Meera’s leaf identifier is 90% accurate. If it is tested on 70 new leaf photos, how many should it get right?
- 3.⚖️ Two leaf identifier models were tested on the same 25 leaf photos. Model A got 22 right and Model B got 16 right. How many percentage points more accurate is Model A?
- 4.📦 Nisha collected 80 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 5.📋 Planning an AI project: which comes first — let it learn patterns or label each example? (a) let it learn patterns (b) label each example
- 6.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to save paper (c) to see if it learned (d) to make it bigger
- 7.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) a new colour screen (c) fewer examples (d) a louder speaker
- 8.📋 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
- 9.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 18 right and Model B got 16 right. How many percentage points more accurate is Model A?
- 10.🎯 Meera’s spam spotter is 60% accurate. If it is tested on 20 new messages, how many should it get right?
- 11.🎯 Aarav’s handwriting reader was tested on 4 new handwritten letters and got 2 right. What is its accuracy in percent?
- 12.📋 Planning an AI project: which comes first — fix it and test again or let it learn patterns? (a) fix it and test again (b) let it learn patterns
- 13.🎯 Kabir’s leaf identifier is 70% accurate. If it is tested on 10 new leaf photos, how many should it get right?
- 14.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 8 right and Model B got 5 right. How many percentage points more accurate is Model A?
- 15.🧪 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
- 16.📋 Planning an AI project: which comes first — set aside test photos or work out the accuracy? (a) set aside test photos (b) work out the accuracy
- 17.📋 Planning an AI project: which comes first — try unseen examples or calculate percent right? (a) try unseen examples (b) calculate percent right
- 18.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 10 right and Model B got 6 right. How many percentage points more accurate is Model A?
- 19.📦 Aarav collected 80 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 20.📦 Diya collected 130 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 21.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 16 right and Model B got 10 right. How many percentage points more accurate is Model A?
- 22.📋 Planning an AI project: which comes first — try unseen examples or work out the accuracy? (a) try unseen examples (b) work out the accuracy
- 23.⚖️ Two leaf identifier models were tested on the same 20 leaf photos. Model A got 20 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 24.🎯 Kabir’s leaf identifier was tested on 4 new leaf photos and got 3 right. What is its accuracy in percent?
- 25.🎯 Ananya’s fruit sorter was tested on 50 new fruit photos and got 48 right. What is its accuracy in percent?
- 26.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 8 right and Model B got 5 right. How many percentage points more accurate is Model A?
- 27.📋 Planning an AI project: which comes first — work out the accuracy or collect fruit photos? (a) work out the accuracy (b) collect fruit photos
- 28.❌ Aarav’s bird-song app was tested on 26 new bird songs and got 22 right. How many did it get wrong?
- 29.📋 Planning an AI project: which comes first — set aside test photos or let it learn patterns? (a) set aside test photos (b) let it learn patterns
- 30.📋 Planning an AI project: which comes first — split train and test or correct bad labels? (a) split train and test (b) correct bad labels
- 31.📋 Planning an AI project: which comes first — pick a question to solve or collect fruit photos? (a) pick a question to solve (b) collect fruit photos
- 32.📋 Planning an AI project: which comes first — calculate percent right or tag each photo by type? (a) calculate percent right (b) tag each photo by type
- 33.📋 Planning an AI project: which comes first — improve data, retest or work out the accuracy? (a) improve data, retest (b) work out the accuracy
- 34.🎯 Kabir’s recycling sorter is 90% accurate. If it is tested on 90 new waste photos, how many should it get right?
- 35.📋 Planning an AI project: which comes first — recheck every label or work out the accuracy? (a) recheck every label (b) work out the accuracy
- 36.⚖️ Two handwriting reader models were tested on the same 50 handwritten letters. Model A got 50 right and Model B got 27 right. How many percentage points more accurate is Model A?
- 37.❌ Meera’s bird-song app was tested on 22 new bird songs and got 21 right. How many did it get wrong?
- 38.🧪 What is accuracy? (a) total − correct (b) total × 2 (c) correct ÷ total × 100 (d) correct + total
- 39.📦 Saanvi collected 150 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 40.🎯 Aarav’s bird-song app is 50% accurate. If it is tested on 90 new bird songs, how many should it get right?
Answer key
- 25
- 63
- 24
- 64
- label each example
- to see if it learned
- more labelled examples
- pick a question to solve
- 8
- 12
- 50
- let it learn patterns
- 7
- 30
- paper and examples
- set aside test photos
- try unseen examples
- 40
- 64
- 104
- 30
- try unseen examples
- 10
- 75
- 96
- 30
- collect fruit photos
- 4
- set aside test photos
- correct bad labels
- pick a question to solve
- tag each photo by type
- work out the accuracy
- 81
- recheck every label
- 46
- 1
- correct ÷ total × 100
- 120
- 45
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students