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.🧪 What is accuracy? (a) total − correct (b) total × 2 (c) correct + total (d) correct ÷ total × 100
- 2.🎯 Ishaan’s fruit sorter is 50% accurate. If it is tested on 20 new fruit photos, how many should it get right?
- 3.📋 Planning an AI project: which comes first — calculate percent right or try unseen examples? (a) calculate percent right (b) try unseen examples
- 4.🎯 Ishaan’s bird-song app was tested on 50 new bird songs and got 29 right. What is its accuracy in percent?
- 5.❌ Ishaan’s fruit sorter was tested on 23 new fruit photos and got 18 right. How many did it get wrong?
- 6.📦 Nisha collected 120 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 7.🎯 Diya’s leaf identifier is 50% accurate. If it is tested on 10 new leaf photos, how many should it get right?
- 8.📋 Planning an AI project: which comes first — let it learn patterns or improve data, retest? (a) let it learn patterns (b) improve data, retest
- 9.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 8 right and Model B got 6 right. How many percentage points more accurate is Model A?
- 10.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 10 right and Model B got 6 right. How many percentage points more accurate is Model A?
- 11.🎯 Meera’s recycling sorter is 50% accurate. If it is tested on 50 new waste photos, how many should it get right?
- 12.🎯 Nisha’s fruit sorter was tested on 25 new fruit photos and got 18 right. What is its accuracy in percent?
- 13.📋 Planning an AI project: which comes first — tag each photo by type or choose what to sort? (a) tag each photo by type (b) choose what to sort
- 14.📋 Planning an AI project: which comes first — fix it and test again or calculate percent right? (a) fix it and test again (b) calculate percent right
- 15.📋 Planning an AI project: which comes first — set aside test photos or test on new photos? (a) set aside test photos (b) test on new photos
- 16.🧪 You can plan a simple AI project with… (a) only a big robot (b) nothing at all (c) a secret password (d) paper and examples
- 17.📦 Rohan collected 180 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 18.🎯 Vihaan’s spam spotter was tested on 10 new messages and got 9 right. What is its accuracy in percent?
- 19.📋 Planning an AI project: which comes first — correct bad labels or tag each photo by type? (a) correct bad labels (b) tag each photo by type
- 20.📋 Planning an AI project: which comes first — calculate percent right or split train and test? (a) calculate percent right (b) split train and test
- 21.📦 Tara collected 140 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 22.🎯 Vihaan’s spam spotter is 60% accurate. If it is tested on 30 new messages, how many should it get right?
- 23.📋 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
- 24.📦 Arjun collected 120 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 25.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 26.📦 Tara collected 120 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 27.⚖️ Two leaf identifier models were tested on the same 25 leaf photos. Model A got 22 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 28.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
- 29.📦 Saanvi collected 170 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 30.📋 Planning an AI project: which comes first — pick a question to solve or split train and test? (a) pick a question to solve (b) split train and test
- 31.📋 Planning an AI project: which comes first — recheck every label or calculate percent right? (a) recheck every label (b) calculate percent right
- 32.🎯 Ananya’s recycling sorter was tested on 20 new waste photos and got 15 right. What is its accuracy in percent?
- 33.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to make it faster (c) to see if it learned (d) to save paper
- 34.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) a new colour screen (c) fewer examples (d) a louder speaker
- 35.📋 Planning an AI project: which comes first — collect fruit photos or label each example? (a) collect fruit photos (b) label each example
- 36.❌ Ananya’s fruit sorter was tested on 34 new fruit photos and got 33 right. How many did it get wrong?
- 37.📋 Planning an AI project: which comes first — train the model or calculate percent right? (a) train the model (b) calculate percent right
- 38.❌ Ishaan’s spam spotter was tested on 43 new messages and got 42 right. How many did it get wrong?
- 39.📋 Planning an AI project: which comes first — set aside test photos or fix it and test again? (a) set aside test photos (b) fix it and test again
- 40.🎯 Rohan’s recycling sorter was tested on 25 new waste photos and got 20 right. What is its accuracy in percent?
Answer key
- correct ÷ total × 100
- 10
- try unseen examples
- 58
- 5
- 96
- 5
- let it learn patterns
- 20
- 40
- 25
- 72
- choose what to sort
- calculate percent right
- set aside test photos
- paper and examples
- 144
- 90
- tag each photo by type
- split train and test
- 112
- 18
- calculate percent right
- 96
- calculate percent right
- 96
- 16
- test on new photos
- 136
- pick a question to solve
- recheck every label
- 75
- to see if it learned
- more labelled examples
- collect fruit photos
- 1
- train the model
- 1
- set aside test photos
- 80
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students