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.🧪 Why must you test a model on examples it has NOT seen? (a) to see if it learned (b) to make it faster (c) to make it bigger (d) to save paper
- 2.📋 Planning an AI project: which comes first — tag each photo by type or collect fruit photos? (a) tag each photo by type (b) collect fruit photos
- 3.📋 Planning an AI project: which comes first — improve data, retest or try unseen examples? (a) improve data, retest (b) try unseen examples
- 4.📋 Planning an AI project: which comes first — fix it and test again or pick a question to solve? (a) fix it and test again (b) pick a question to solve
- 5.📋 Planning an AI project: which comes first — work out the accuracy or test on new photos? (a) work out the accuracy (b) test on new photos
- 6.📋 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
- 7.🎯 Kabir’s leaf identifier was tested on 4 new leaf photos and got 2 right. What is its accuracy in percent?
- 8.📋 Planning an AI project: which comes first — test on new photos or calculate percent right? (a) test on new photos (b) calculate percent right
- 9.📋 Planning an AI project: which comes first — recheck every label or label each example? (a) recheck every label (b) label each example
- 10.📋 Planning an AI project: which comes first — work out the accuracy or try unseen examples? (a) work out the accuracy (b) try unseen examples
- 11.❌ Kabir’s fruit sorter was tested on 37 new fruit photos and got 32 right. How many did it get wrong?
- 12.❌ Rohan’s handwriting reader was tested on 31 new handwritten letters and got 28 right. How many did it get wrong?
- 13.📦 Tara collected 130 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 14.🧪 You can plan a simple AI project with… (a) nothing at all (b) only a big robot (c) a secret password (d) paper and examples
- 15.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 40 right and Model B got 30 right. How many percentage points more accurate is Model A?
- 16.❌ Ishaan’s recycling sorter was tested on 39 new waste photos and got 31 right. How many did it get wrong?
- 17.📋 Planning an AI project: which comes first — choose what to sort or work out the accuracy? (a) choose what to sort (b) work out the accuracy
- 18.🎯 Rohan’s fruit sorter is 50% accurate. If it is tested on 60 new fruit photos, how many should it get right?
- 19.🎯 Saanvi’s fruit sorter was tested on 10 new fruit photos and got 5 right. What is its accuracy in percent?
- 20.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 15 right and Model B got 12 right. How many percentage points more accurate is Model A?
- 21.📋 Planning an AI project: which comes first — fix it and test again or train the model? (a) fix it and test again (b) train the model
- 22.📋 Planning an AI project: which comes first — improve data, retest or train the model? (a) improve data, retest (b) train the model
- 23.📋 Planning an AI project: which comes first — let it learn patterns or recheck every label? (a) let it learn patterns (b) recheck every label
- 24.📦 Aarav collected 170 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 25.🎯 Arjun’s bird-song app is 50% accurate. If it is tested on 80 new bird songs, how many should it get right?
- 26.📋 Planning an AI project: which comes first — collect fruit photos or set aside test photos? (a) collect fruit photos (b) set aside test photos
- 27.🎯 Ananya’s handwriting reader was tested on 10 new handwritten letters and got 6 right. What is its accuracy in percent?
- 28.📋 Planning an AI project: which comes first — improve data, retest or work out the accuracy? (a) improve data, retest (b) work out the accuracy
- 29.🎯 Diya’s leaf identifier was tested on 5 new leaf photos and got 4 right. What is its accuracy in percent?
- 30.📋 Planning an AI project: which comes first — gather many examples or test on new photos? (a) gather many examples (b) test on new photos
- 31.📋 Planning an AI project: which comes first — correct bad labels or let it learn patterns? (a) correct bad labels (b) let it learn patterns
- 32.🎯 Meera’s spam spotter is 80% accurate. If it is tested on 80 new messages, how many should it get right?
- 33.🎯 Kabir’s spam spotter was tested on 20 new messages and got 20 right. What is its accuracy in percent?
- 34.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 22 right and Model B got 19 right. How many percentage points more accurate is Model A?
- 35.🎯 Arjun’s bird-song app was tested on 25 new bird songs and got 22 right. What is its accuracy in percent?
- 36.📋 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
- 37.🎯 Ananya’s bird-song app was tested on 25 new bird songs and got 18 right. What is its accuracy in percent?
- 38.📋 Planning an AI project: which comes first — set aside test photos or choose what to sort? (a) set aside test photos (b) choose what to sort
- 39.❌ Vihaan’s spam spotter was tested on 19 new messages and got 12 right. How many did it get wrong?
- 40.📦 Ishaan collected 150 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
Answer key
- to see if it learned
- collect fruit photos
- try unseen examples
- pick a question to solve
- test on new photos
- calculate percent right
- 50
- test on new photos
- label each example
- try unseen examples
- 5
- 3
- 104
- paper and examples
- 20
- 8
- choose what to sort
- 30
- 50
- 15
- train the model
- train the model
- recheck every label
- 136
- 40
- collect fruit photos
- 60
- work out the accuracy
- 80
- gather many examples
- correct bad labels
- 64
- 100
- 12
- 88
- tag each photo by type
- 72
- choose what to sort
- 7
- 120
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students