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.❌ Tara’s spam spotter was tested on 50 new messages and got 49 right. How many did it get wrong?
- 2.📋 Planning an AI project: which comes first — tag each photo by type or work out the accuracy? (a) tag each photo by type (b) work out the accuracy
- 3.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 17 right and Model B got 15 right. How many percentage points more accurate is Model A?
- 4.❌ Tara’s recycling sorter was tested on 49 new waste photos and got 45 right. How many did it get wrong?
- 5.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 13 right and Model B got 11 right. How many percentage points more accurate is Model A?
- 6.📋 Planning an AI project: which comes first — pick a question to solve or tag each photo by type? (a) pick a question to solve (b) tag each photo by type
- 7.❌ Ananya’s spam spotter was tested on 43 new messages and got 41 right. How many did it get wrong?
- 8.📋 Planning an AI project: which comes first — choose what to sort or split train and test? (a) choose what to sort (b) split train and test
- 9.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 10.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 8 right and Model B got 5 right. How many percentage points more accurate is Model A?
- 11.📋 Planning an AI project: which comes first — label each example or improve data, retest? (a) label each example (b) improve data, retest
- 12.🎯 Ananya’s fruit sorter was tested on 4 new fruit photos and got 2 right. What is its accuracy in percent?
- 13.🎯 Meera’s leaf identifier is 50% accurate. If it is tested on 100 new leaf photos, how many should it get right?
- 14.❌ Nisha’s handwriting reader was tested on 14 new handwritten letters and got 11 right. How many did it get wrong?
- 15.📋 Planning an AI project: which comes first — try unseen examples or work out the accuracy? (a) try unseen examples (b) work out the accuracy
- 16.📋 Planning an AI project: which comes first — tag each photo by type or correct bad labels? (a) tag each photo by type (b) correct bad labels
- 17.🧪 You can plan a simple AI project with… (a) only a big robot (b) paper and examples (c) nothing at all (d) a secret password
- 18.🧪 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
- 19.📋 Planning an AI project: which comes first — gather many examples or work out the accuracy? (a) gather many examples (b) work out the accuracy
- 20.📋 Planning an AI project: which comes first — calculate percent right or gather many examples? (a) calculate percent right (b) gather many examples
- 21.📋 Planning an AI project: which comes first — train the model or pick a question to solve? (a) train the model (b) pick a question to solve
- 22.📦 Aarav collected 170 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 23.🎯 Ananya’s handwriting reader was tested on 25 new handwritten letters and got 18 right. What is its accuracy in percent?
- 24.📋 Planning an AI project: which comes first — test on new photos or correct bad labels? (a) test on new photos (b) correct bad labels
- 25.📦 Saanvi collected 190 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 26.🎯 Saanvi’s leaf identifier was tested on 20 new leaf photos and got 19 right. What is its accuracy in percent?
- 27.📋 Planning an AI project: which comes first — split train and test or let it learn patterns? (a) split train and test (b) let it learn patterns
- 28.📦 Arjun collected 170 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 29.🧪 What is accuracy? (a) correct + total (b) total × 2 (c) correct ÷ total × 100 (d) total − correct
- 30.❌ Rohan’s bird-song app was tested on 30 new bird songs and got 28 right. How many did it get wrong?
- 31.❌ Tara’s recycling sorter was tested on 24 new waste photos and got 19 right. How many did it get wrong?
- 32.🎯 Aarav’s spam spotter is 70% accurate. If it is tested on 100 new messages, how many should it get right?
- 33.📋 Planning an AI project: which comes first — improve data, retest or correct bad labels? (a) improve data, retest (b) correct bad labels
- 34.❌ Kabir’s bird-song app was tested on 33 new bird songs and got 29 right. How many did it get wrong?
- 35.📋 Planning an AI project: which comes first — recheck every label or choose what to sort? (a) recheck every label (b) choose what to sort
- 36.⚖️ Two recycling sorter models were tested on the same 10 waste photos. Model A got 10 right and Model B got 8 right. How many percentage points more accurate is Model A?
- 37.📋 Planning an AI project: which comes first — correct bad labels or set aside test photos? (a) correct bad labels (b) set aside test photos
- 38.📋 Planning an AI project: which comes first — pick a question to solve or label each example? (a) pick a question to solve (b) label each example
- 39.🎯 Nisha’s recycling sorter is 90% accurate. If it is tested on 50 new waste photos, how many should it get right?
- 40.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 23 right and Model B got 22 right. How many percentage points more accurate is Model A?
Answer key
- 1
- tag each photo by type
- 10
- 4
- 10
- pick a question to solve
- 2
- choose what to sort
- calculate percent right
- 30
- label each example
- 50
- 50
- 3
- try unseen examples
- tag each photo by type
- paper and examples
- more labelled examples
- gather many examples
- gather many examples
- pick a question to solve
- 136
- 72
- correct bad labels
- 152
- 95
- split train and test
- 136
- correct ÷ total × 100
- 2
- 5
- 70
- correct bad labels
- 4
- choose what to sort
- 20
- correct bad labels
- pick a question to solve
- 45
- 4
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students