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.🎯 Saanvi’s fruit sorter is 50% accurate. If it is tested on 20 new fruit photos, how many should it get right?
- 2.❌ Saanvi’s bird-song app was tested on 43 new bird songs and got 37 right. How many did it get wrong?
- 3.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) fewer examples (c) a new colour screen (d) a louder speaker
- 4.📦 Ishaan collected 60 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 5.❌ Rohan’s fruit sorter was tested on 18 new fruit photos and got 14 right. How many did it get wrong?
- 6.🎯 Diya’s spam spotter was tested on 25 new messages and got 24 right. What is its accuracy in percent?
- 7.🧪 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
- 8.🧪 What is accuracy? (a) correct + total (b) correct ÷ total × 100 (c) total × 2 (d) total − correct
- 9.📋 Planning an AI project: which comes first — work out the accuracy or set aside test photos? (a) work out the accuracy (b) set aside test photos
- 10.📦 Kabir collected 60 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 11.❌ Aarav’s spam spotter was tested on 27 new messages and got 24 right. How many did it get wrong?
- 12.📋 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
- 13.📦 Tara collected 40 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 14.📋 Planning an AI project: which comes first — test on new photos or calculate percent right? (a) test on new photos (b) calculate percent right
- 15.🎯 Ananya’s leaf identifier is 50% accurate. If it is tested on 90 new leaf photos, how many should it get right?
- 16.📋 Planning an AI project: which comes first — correct bad labels or test on new photos? (a) correct bad labels (b) test on new photos
- 17.❌ Aarav’s bird-song app was tested on 25 new bird songs and got 22 right. How many did it get wrong?
- 18.⚖️ Two handwriting reader models were tested on the same 50 handwritten letters. Model A got 44 right and Model B got 29 right. How many percentage points more accurate is Model A?
- 19.📋 Planning an AI project: which comes first — label each example or improve data, retest? (a) label each example (b) improve data, retest
- 20.📋 Planning an AI project: which comes first — fix it and test again or choose what to sort? (a) fix it and test again (b) choose what to sort
- 21.📋 Planning an AI project: which comes first — work out the accuracy or fix it and test again? (a) work out the accuracy (b) fix it and test again
- 22.🎯 Vihaan’s handwriting reader is 90% accurate. If it is tested on 20 new handwritten letters, how many should it get right?
- 23.🎯 Meera’s fruit sorter was tested on 5 new fruit photos and got 5 right. What is its accuracy in percent?
- 24.📋 Planning an AI project: which comes first — label each example or split train and test? (a) label each example (b) split train and test
- 25.🧪 You can plan a simple AI project with… (a) nothing at all (b) paper and examples (c) a secret password (d) only a big robot
- 26.📋 Planning an AI project: which comes first — collect fruit photos or pick a question to solve? (a) collect fruit photos (b) pick a question to solve
- 27.📦 Ishaan collected 180 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 28.🎯 Ishaan’s recycling sorter is 70% accurate. If it is tested on 50 new waste photos, how many should it get right?
- 29.📋 Planning an AI project: which comes first — test on new photos or choose what to sort? (a) test on new photos (b) choose what to sort
- 30.📋 Planning an AI project: which comes first — train the model or correct bad labels? (a) train the model (b) correct bad labels
- 31.⚖️ Two recycling sorter models were tested on the same 25 waste photos. Model A got 25 right and Model B got 24 right. How many percentage points more accurate is Model A?
- 32.📦 Diya collected 80 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 33.❌ Saanvi’s bird-song app was tested on 17 new bird songs and got 16 right. How many did it get wrong?
- 34.⚖️ Two recycling sorter models were tested on the same 50 waste photos. Model A got 45 right and Model B got 30 right. How many percentage points more accurate is Model A?
- 35.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
- 36.❌ Nisha’s fruit sorter was tested on 50 new fruit photos and got 47 right. How many did it get wrong?
- 37.📋 Planning an AI project: which comes first — gather many examples or recheck every label? (a) gather many examples (b) recheck every label
- 38.🎯 Aarav’s bird-song app is 80% accurate. If it is tested on 60 new bird songs, how many should it get right?
- 39.⚖️ Two handwriting reader models were tested on the same 10 handwritten letters. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
- 40.🎯 Rohan’s spam spotter was tested on 50 new messages and got 38 right. What is its accuracy in percent?
Answer key
- 10
- 6
- more labelled examples
- 48
- 4
- 96
- to see if it learned
- correct ÷ total × 100
- set aside test photos
- 48
- 3
- work out the accuracy
- 32
- test on new photos
- 45
- correct bad labels
- 3
- 30
- label each example
- choose what to sort
- work out the accuracy
- 18
- 100
- label each example
- paper and examples
- pick a question to solve
- 144
- 35
- choose what to sort
- correct bad labels
- 4
- 64
- 1
- 30
- 10
- 3
- gather many examples
- 48
- 10
- 76
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students