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.📦 Ishaan collected 50 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 2.🎯 Diya’s handwriting reader is 50% accurate. If it is tested on 80 new handwritten letters, how many should it get right?
- 3.📋 Planning an AI project: which comes first — gather many examples or correct bad labels? (a) gather many examples (b) correct bad labels
- 4.📋 Planning an AI project: which comes first — improve data, retest or split train and test? (a) improve data, retest (b) split train and test
- 5.🎯 Rohan’s fruit sorter is 70% accurate. If it is tested on 10 new fruit photos, how many should it get right?
- 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.❌ Vihaan’s fruit sorter was tested on 31 new fruit photos and got 27 right. How many did it get wrong?
- 8.❌ Kabir’s spam spotter was tested on 49 new messages and got 44 right. How many did it get wrong?
- 9.📋 Planning an AI project: which comes first — pick a question to solve or set aside test photos? (a) pick a question to solve (b) set aside test photos
- 10.🎯 Ishaan’s spam spotter was tested on 4 new messages and got 2 right. What is its accuracy in percent?
- 11.⚖️ Two bird-song app models were tested on the same 20 bird songs. Model A got 19 right and Model B got 17 right. How many percentage points more accurate is Model A?
- 12.🧪 What is accuracy? (a) total × 2 (b) correct ÷ total × 100 (c) total − correct (d) correct + total
- 13.📋 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
- 14.📋 Planning an AI project: which comes first — calculate percent right or let it learn patterns? (a) calculate percent right (b) let it learn patterns
- 15.🧪 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
- 16.❌ Arjun’s bird-song app was tested on 18 new bird songs and got 11 right. How many did it get wrong?
- 17.❌ Kabir’s recycling sorter was tested on 24 new waste photos and got 21 right. How many did it get wrong?
- 18.📋 Planning an AI project: which comes first — test on new photos or calculate percent right? (a) test on new photos (b) calculate percent right
- 19.⚖️ Two spam spotter models were tested on the same 25 messages. Model A got 20 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 20.📋 Planning an AI project: which comes first — recheck every label or gather many examples? (a) recheck every label (b) gather many examples
- 21.📋 Planning an AI project: which comes first — test on new photos or fix it and test again? (a) test on new photos (b) fix it and test again
- 22.📋 Planning an AI project: which comes first — correct bad labels or gather many examples? (a) correct bad labels (b) gather many examples
- 23.📋 Planning an AI project: which comes first — train the model or split train and test? (a) train the model (b) split train and test
- 24.📋 Planning an AI project: which comes first — work out the accuracy or gather many examples? (a) work out the accuracy (b) gather many examples
- 25.📦 Saanvi collected 200 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 26.📋 Planning an AI project: which comes first — let it learn patterns or correct bad labels? (a) let it learn patterns (b) correct bad labels
- 27.📦 Ananya collected 170 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 28.⚖️ Two spam spotter models were tested on the same 25 messages. Model A got 24 right and Model B got 15 right. How many percentage points more accurate is Model A?
- 29.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 15 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 30.📋 Planning an AI project: which comes first — gather many examples or set aside test photos? (a) gather many examples (b) set aside test photos
- 31.❌ Tara’s recycling sorter was tested on 35 new waste photos and got 34 right. How many did it get wrong?
- 32.📋 Planning an AI project: which comes first — split train and test or recheck every label? (a) split train and test (b) recheck every label
- 33.🎯 Saanvi’s fruit sorter was tested on 4 new fruit photos and got 4 right. What is its accuracy in percent?
- 34.🎯 Saanvi’s recycling sorter was tested on 10 new waste photos and got 8 right. What is its accuracy in percent?
- 35.📋 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
- 36.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) fewer examples (b) a new colour screen (c) a louder speaker (d) more labelled examples
- 37.🎯 Ishaan’s handwriting reader is 80% accurate. If it is tested on 70 new handwritten letters, how many should it get right?
- 38.🎯 Diya’s fruit sorter was tested on 5 new fruit photos and got 3 right. What is its accuracy in percent?
- 39.⚖️ Two fruit sorter models were tested on the same 50 fruit photos. Model A got 50 right and Model B got 44 right. How many percentage points more accurate is Model A?
- 40.📋 Planning an AI project: which comes first — choose what to sort or try unseen examples? (a) choose what to sort (b) try unseen examples
Answer key
- 40
- 40
- gather many examples
- split train and test
- 7
- to see if it learned
- 4
- 5
- pick a question to solve
- 50
- 10
- correct ÷ total × 100
- choose what to sort
- let it learn patterns
- paper and examples
- 7
- 3
- test on new photos
- 8
- gather many examples
- test on new photos
- gather many examples
- split train and test
- gather many examples
- 160
- correct bad labels
- 136
- 36
- 8
- gather many examples
- 1
- recheck every label
- 100
- 80
- work out the accuracy
- more labelled examples
- 56
- 60
- 12
- choose what to sort
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students