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 — recheck every label or let it learn patterns? (a) recheck every label (b) let it learn patterns
- 2.🎯 Vihaan’s spam spotter is 70% accurate. If it is tested on 30 new messages, how many should it get right?
- 3.📦 Ananya collected 130 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 4.🎯 Kabir’s fruit sorter was tested on 10 new fruit photos and got 7 right. What is its accuracy in percent?
- 5.❌ Saanvi’s leaf identifier was tested on 29 new leaf photos and got 27 right. How many did it get wrong?
- 6.⚖️ Two handwriting reader models were tested on the same 10 handwritten letters. Model A got 10 right and Model B got 5 right. How many percentage points more accurate is Model A?
- 7.🎯 Vihaan’s handwriting reader is 90% accurate. If it is tested on 80 new handwritten letters, how many should it get right?
- 8.🎯 Vihaan’s fruit sorter was tested on 50 new fruit photos and got 35 right. What is its accuracy in percent?
- 9.❌ Saanvi’s leaf identifier was tested on 16 new leaf photos and got 15 right. How many did it get wrong?
- 10.⚖️ Two recycling sorter models were tested on the same 50 waste photos. Model A got 50 right and Model B got 47 right. How many percentage points more accurate is Model A?
- 11.📋 Planning an AI project: which comes first — fix it and test again or split train and test? (a) fix it and test again (b) split train and test
- 12.🧪 What is accuracy? (a) total × 2 (b) correct ÷ total × 100 (c) total − correct (d) correct + total
- 13.⚖️ Two recycling sorter models were tested on the same 25 waste photos. Model A got 15 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 14.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 7 right and Model B got 6 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) nothing at all (c) paper and examples (d) a secret password
- 16.⚖️ Two handwriting reader models were tested on the same 20 handwritten letters. Model A got 20 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 17.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to make it bigger (c) to see if it learned (d) to save paper
- 18.📦 Diya collected 200 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 19.📋 Planning an AI project: which comes first — train the model or tag each photo by type? (a) train the model (b) tag each photo by type
- 20.📋 Planning an AI project: which comes first — collect fruit photos or recheck every label? (a) collect fruit photos (b) recheck every label
- 21.📦 Nisha collected 40 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 22.⚖️ Two fruit sorter models were tested on the same 50 fruit photos. Model A got 48 right and Model B got 31 right. How many percentage points more accurate is Model A?
- 23.📋 Planning an AI project: which comes first — work out the accuracy or train the model? (a) work out the accuracy (b) train the model
- 24.❌ Diya’s bird-song app was tested on 49 new bird songs and got 41 right. How many did it get wrong?
- 25.📋 Planning an AI project: which comes first — try unseen examples or let it learn patterns? (a) try unseen examples (b) let it learn patterns
- 26.🎯 Ishaan’s bird-song app is 50% accurate. If it is tested on 60 new bird songs, how many should it get right?
- 27.❌ Kabir’s spam spotter was tested on 14 new messages and got 11 right. How many did it get wrong?
- 28.📋 Planning an AI project: which comes first — test on new photos or correct bad labels? (a) test on new photos (b) correct bad labels
- 29.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 30.❌ Kabir’s fruit sorter was tested on 18 new fruit photos and got 14 right. How many did it get wrong?
- 31.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 9 right and Model B got 7 right. How many percentage points more accurate is Model A?
- 32.📋 Planning an AI project: which comes first — let it learn patterns or gather many examples? (a) let it learn patterns (b) gather many examples
- 33.📦 Tara collected 200 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 34.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 22 right and Model B got 16 right. How many percentage points more accurate is Model A?
- 35.❌ Ananya’s spam spotter was tested on 22 new messages and got 13 right. How many did it get wrong?
- 36.📦 Kabir collected 70 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 37.🎯 Ishaan’s recycling sorter is 90% accurate. If it is tested on 40 new waste photos, how many should it get right?
- 38.🎯 Kabir’s fruit sorter was tested on 50 new fruit photos and got 43 right. What is its accuracy in percent?
- 39.📦 Nisha collected 190 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 40.🎯 Meera’s handwriting reader is 50% accurate. If it is tested on 40 new handwritten letters, how many should it get right?
Answer key
- recheck every label
- 21
- 104
- 70
- 2
- 50
- 72
- 70
- 1
- 6
- split train and test
- correct ÷ total × 100
- 8
- 10
- paper and examples
- 10
- to see if it learned
- 160
- tag each photo by type
- collect fruit photos
- 32
- 34
- train the model
- 8
- let it learn patterns
- 30
- 3
- correct bad labels
- calculate percent right
- 4
- 20
- gather many examples
- 160
- 24
- 9
- 56
- 36
- 86
- 152
- 20
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students