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 60 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 2.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to save paper (c) to see if it learned (d) to make it faster
- 3.🧪 What is accuracy? (a) total − correct (b) total × 2 (c) correct + total (d) correct ÷ total × 100
- 4.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) more labelled examples (c) fewer examples (d) a new colour screen
- 5.📦 Diya collected 200 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 6.🎯 Rohan’s spam spotter was tested on 50 new messages and got 26 right. What is its accuracy in percent?
- 7.📋 Planning an AI project: which comes first — calculate percent right or try unseen examples? (a) calculate percent right (b) try unseen examples
- 8.🧪 You can plan a simple AI project with… (a) a secret password (b) nothing at all (c) paper and examples (d) only a big robot
- 9.📋 Planning an AI project: which comes first — train the model or work out the accuracy? (a) train the model (b) work out the accuracy
- 10.❌ Arjun’s handwriting reader was tested on 42 new handwritten letters and got 34 right. How many did it get wrong?
- 11.🎯 Nisha’s fruit sorter is 50% accurate. If it is tested on 80 new fruit photos, how many should it get right?
- 12.❌ Nisha’s bird-song app was tested on 40 new bird songs and got 35 right. How many did it get wrong?
- 13.📋 Planning an AI project: which comes first — correct bad labels or improve data, retest? (a) correct bad labels (b) improve data, retest
- 14.🎯 Tara’s handwriting reader was tested on 50 new handwritten letters and got 48 right. What is its accuracy in percent?
- 15.📋 Planning an AI project: which comes first — set aside test photos or gather many examples? (a) set aside test photos (b) gather many examples
- 16.🎯 Diya’s leaf identifier was tested on 20 new leaf photos and got 17 right. What is its accuracy in percent?
- 17.🎯 Rohan’s recycling sorter is 50% accurate. If it is tested on 100 new waste photos, how many should it get right?
- 18.⚖️ 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?
- 19.📋 Planning an AI project: which comes first — work out the accuracy or tag each photo by type? (a) work out the accuracy (b) tag each photo by type
- 20.🎯 Meera’s fruit sorter is 80% accurate. If it is tested on 10 new fruit photos, how many should it get right?
- 21.🎯 Diya’s bird-song app is 60% accurate. If it is tested on 70 new bird songs, how many should it get right?
- 22.📦 Rohan collected 180 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 23.📋 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
- 24.⚖️ Two spam spotter models were tested on the same 10 messages. Model A got 10 right and Model B got 7 right. How many percentage points more accurate is Model A?
- 25.📦 Kabir collected 140 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 26.🎯 Diya’s recycling sorter is 70% accurate. If it is tested on 20 new waste photos, how many should it get right?
- 27.🎯 Aarav’s spam spotter was tested on 50 new messages and got 43 right. What is its accuracy in percent?
- 28.🎯 Arjun’s bird-song app was tested on 4 new bird songs and got 4 right. What is its accuracy in percent?
- 29.📋 Planning an AI project: which comes first — train the model or set aside test photos? (a) train the model (b) set aside test photos
- 30.🎯 Ananya’s handwriting reader is 60% accurate. If it is tested on 30 new handwritten letters, how many should it get right?
- 31.📦 Arjun collected 90 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 32.📋 Planning an AI project: which comes first — label each example or recheck every label? (a) label each example (b) recheck every label
- 33.📋 Planning an AI project: which comes first — fix it and test again or correct bad labels? (a) fix it and test again (b) correct bad labels
- 34.📋 Planning an AI project: which comes first — try unseen examples or calculate percent right? (a) try unseen examples (b) calculate percent right
- 35.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 36.📋 Planning an AI project: which comes first — label each example or calculate percent right? (a) label each example (b) calculate percent right
- 37.⚖️ Two leaf identifier models were tested on the same 50 leaf photos. Model A got 38 right and Model B got 27 right. How many percentage points more accurate is Model A?
- 38.⚖️ Two recycling sorter models were tested on the same 25 waste photos. Model A got 23 right and Model B got 16 right. How many percentage points more accurate is Model A?
- 39.📋 Planning an AI project: which comes first — correct bad labels or label each example? (a) correct bad labels (b) label each example
- 40.🎯 Nisha’s bird-song app was tested on 4 new bird songs and got 2 right. What is its accuracy in percent?
Answer key
- 48
- to see if it learned
- correct ÷ total × 100
- more labelled examples
- 160
- 52
- try unseen examples
- paper and examples
- train the model
- 8
- 40
- 5
- correct bad labels
- 96
- gather many examples
- 85
- 50
- 4
- tag each photo by type
- 8
- 42
- 144
- tag each photo by type
- 30
- 112
- 14
- 86
- 100
- set aside test photos
- 18
- 72
- label each example
- correct bad labels
- try unseen examples
- calculate percent right
- label each example
- 22
- 28
- label each example
- 50
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students