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 — fix it and test again or work out the accuracy? (a) fix it and test again (b) work out the accuracy
- 2.❌ Kabir’s handwriting reader was tested on 45 new handwritten letters and got 41 right. How many did it get wrong?
- 3.❌ Saanvi’s recycling sorter was tested on 20 new waste photos and got 19 right. How many did it get wrong?
- 4.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
- 5.📦 Tara collected 170 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 6.🎯 Tara’s handwriting reader is 50% accurate. If it is tested on 30 new handwritten letters, how many should it get right?
- 7.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 8.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to see if it learned (c) to save paper (d) to make it faster
- 9.⚖️ Two spam spotter models were tested on the same 25 messages. Model A got 23 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 10.❌ Meera’s leaf identifier was tested on 31 new leaf photos and got 24 right. How many did it get wrong?
- 11.🎯 Ishaan’s handwriting reader was tested on 5 new handwritten letters and got 4 right. What is its accuracy in percent?
- 12.⚖️ Two leaf identifier models were tested on the same 50 leaf photos. Model A got 48 right and Model B got 46 right. How many percentage points more accurate is Model A?
- 13.📋 Planning an AI project: which comes first — split train and test or calculate percent right? (a) split train and test (b) calculate percent right
- 14.📋 Planning an AI project: which comes first — fix it and test again or try unseen examples? (a) fix it and test again (b) try unseen examples
- 15.🎯 Saanvi’s recycling sorter was tested on 25 new waste photos and got 15 right. What is its accuracy in percent?
- 16.⚖️ Two spam spotter models were tested on the same 50 messages. Model A got 50 right and Model B got 49 right. How many percentage points more accurate is Model A?
- 17.📦 Meera collected 200 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 18.❌ Diya’s fruit sorter was tested on 40 new fruit photos and got 34 right. How many did it get wrong?
- 19.📦 Aarav collected 190 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 20.🧪 What is accuracy? (a) total − correct (b) correct ÷ total × 100 (c) correct + total (d) total × 2
- 21.❌ Arjun’s bird-song app was tested on 45 new bird songs and got 40 right. How many did it get wrong?
- 22.📋 Planning an AI project: which comes first — fix it and test again or test on new photos? (a) fix it and test again (b) test on new photos
- 23.📦 Kabir collected 60 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 24.🎯 Kabir’s fruit sorter is 90% accurate. If it is tested on 40 new fruit photos, how many should it get right?
- 25.🧪 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
- 26.📋 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
- 27.📋 Planning an AI project: which comes first — test on new photos or improve data, retest? (a) test on new photos (b) improve data, retest
- 28.📋 Planning an AI project: which comes first — fix it and test again or recheck every label? (a) fix it and test again (b) recheck every label
- 29.📋 Planning an AI project: which comes first — gather many examples or work out the accuracy? (a) gather many examples (b) work out the accuracy
- 30.📦 Nisha collected 190 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 31.📦 Ananya collected 100 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 32.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) fewer examples (c) a new colour screen (d) more labelled examples
- 33.🎯 Diya’s bird-song app is 60% accurate. If it is tested on 40 new bird songs, how many should it get right?
- 34.📋 Planning an AI project: which comes first — collect fruit photos or let it learn patterns? (a) collect fruit photos (b) let it learn patterns
- 35.❌ Ishaan’s fruit sorter was tested on 38 new fruit photos and got 34 right. How many did it get wrong?
- 36.📋 Planning an AI project: which comes first — recheck every label or try unseen examples? (a) recheck every label (b) try unseen examples
- 37.🎯 Aarav’s spam spotter was tested on 5 new messages and got 5 right. What is its accuracy in percent?
- 38.📋 Planning an AI project: which comes first — try unseen examples or split train and test? (a) try unseen examples (b) split train and test
- 39.📦 Kabir collected 200 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 40.📦 Kabir collected 130 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
Answer key
- work out the accuracy
- 4
- 1
- test on new photos
- 136
- 15
- calculate percent right
- to see if it learned
- 40
- 7
- 80
- 4
- split train and test
- try unseen examples
- 60
- 2
- 160
- 6
- 152
- correct ÷ total × 100
- 5
- test on new photos
- 48
- 36
- paper and examples
- split train and test
- test on new photos
- recheck every label
- gather many examples
- 152
- 80
- more labelled examples
- 24
- collect fruit photos
- 4
- recheck every label
- 100
- split train and test
- 160
- 104
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students