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.⚖️ Two recycling sorter models were tested on the same 20 waste photos. Model A got 20 right and Model B got 15 right. How many percentage points more accurate is Model A?
- 2.🧪 You can plan a simple AI project with… (a) a secret password (b) paper and examples (c) nothing at all (d) only a big robot
- 3.⚖️ Two bird-song app models were tested on the same 10 bird songs. Model A got 8 right and Model B got 7 right. How many percentage points more accurate is Model A?
- 4.📋 Planning an AI project: which comes first — let it learn patterns or split train and test? (a) let it learn patterns (b) split train and test
- 5.📋 Planning an AI project: which comes first — choose what to sort or tag each photo by type? (a) choose what to sort (b) tag each photo by type
- 6.🧪 What is accuracy? (a) total × 2 (b) correct ÷ total × 100 (c) total − correct (d) correct + total
- 7.📋 Planning an AI project: which comes first — tag each photo by type or pick a question to solve? (a) tag each photo by type (b) pick a question to solve
- 8.❌ Saanvi’s bird-song app was tested on 48 new bird songs and got 39 right. How many did it get wrong?
- 9.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) fewer examples (c) a louder speaker (d) a new colour screen
- 10.🎯 Ananya’s bird-song app is 80% accurate. If it is tested on 100 new bird songs, how many should it get right?
- 11.📋 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
- 12.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 18 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 13.❌ Saanvi’s recycling sorter was tested on 18 new waste photos and got 17 right. How many did it get wrong?
- 14.📋 Planning an AI project: which comes first — split train and test or gather many examples? (a) split train and test (b) gather many examples
- 15.📋 Planning an AI project: which comes first — try unseen examples or tag each photo by type? (a) try unseen examples (b) tag each photo by type
- 16.🎯 Kabir’s leaf identifier is 70% accurate. If it is tested on 10 new leaf photos, how many should it get right?
- 17.📦 Rohan collected 160 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 18.📋 Planning an AI project: which comes first — improve data, retest or try unseen examples? (a) improve data, retest (b) try unseen examples
- 19.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
- 20.📋 Planning an AI project: which comes first — test on new photos or correct bad labels? (a) test on new photos (b) correct bad labels
- 21.🎯 Ishaan’s leaf identifier is 60% accurate. If it is tested on 20 new leaf photos, how many should it get right?
- 22.📋 Planning an AI project: which comes first — work out the accuracy or improve data, retest? (a) work out the accuracy (b) improve data, retest
- 23.📋 Planning an AI project: which comes first — tag each photo by type or let it learn patterns? (a) tag each photo by type (b) let it learn patterns
- 24.📦 Ishaan collected 80 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 — pick a question to solve or label each example? (a) pick a question to solve (b) label each example
- 26.📋 Planning an AI project: which comes first — test on new photos or train the model? (a) test on new photos (b) train the model
- 27.📦 Aarav collected 190 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 28.📦 Ishaan collected 150 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 29.📋 Planning an AI project: which comes first — test on new photos or calculate percent right? (a) test on new photos (b) calculate percent right
- 30.🧪 Why must you test a model on examples it has NOT seen? (a) to see if it learned (b) to save paper (c) to make it faster (d) to make it bigger
- 31.🎯 Nisha’s spam spotter was tested on 25 new messages and got 20 right. What is its accuracy in percent?
- 32.🎯 Saanvi’s fruit sorter was tested on 5 new fruit photos and got 4 right. What is its accuracy in percent?
- 33.🎯 Ananya’s handwriting reader was tested on 5 new handwritten letters and got 3 right. What is its accuracy in percent?
- 34.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 9 right and Model B got 6 right. How many percentage points more accurate is Model A?
- 35.🎯 Saanvi’s leaf identifier was tested on 20 new leaf photos and got 18 right. What is its accuracy in percent?
- 36.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
- 37.🎯 Diya’s fruit sorter was tested on 20 new fruit photos and got 12 right. What is its accuracy in percent?
- 38.🎯 Ananya’s leaf identifier was tested on 5 new leaf photos and got 3 right. What is its accuracy in percent?
- 39.🎯 Kabir’s fruit sorter is 50% accurate. If it is tested on 90 new fruit photos, how many should it get right?
- 40.📋 Planning an AI project: which comes first — calculate percent right or test on new photos? (a) calculate percent right (b) test on new photos
Answer key
- 25
- paper and examples
- 10
- split train and test
- choose what to sort
- correct ÷ total × 100
- pick a question to solve
- 9
- more labelled examples
- 80
- calculate percent right
- 25
- 1
- gather many examples
- tag each photo by type
- 7
- 128
- try unseen examples
- train the model
- correct bad labels
- 12
- work out the accuracy
- tag each photo by type
- 64
- pick a question to solve
- train the model
- 152
- 120
- test on new photos
- to see if it learned
- 80
- 80
- 60
- 30
- 90
- test on new photos
- 60
- 60
- 45
- test on new photos
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students