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.📋 Planning an AI project: which comes first — choose what to sort or recheck every label? (a) choose what to sort (b) recheck every label
- 2.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 19 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 3.🧪 You can plan a simple AI project with… (a) a secret password (b) paper and examples (c) only a big robot (d) nothing at all
- 4.🎯 Meera’s fruit sorter was tested on 25 new fruit photos and got 17 right. What is its accuracy in percent?
- 5.📋 Planning an AI project: which comes first — split train and test or test on new photos? (a) split train and test (b) test on new photos
- 6.🎯 Vihaan’s bird-song app was tested on 50 new bird songs and got 32 right. What is its accuracy in percent?
- 7.❌ Kabir’s leaf identifier was tested on 23 new leaf photos and got 15 right. How many did it get wrong?
- 8.📋 Planning an AI project: which comes first — split train and test or recheck every label? (a) split train and test (b) recheck every label
- 9.📋 Planning an AI project: which comes first — correct bad labels or work out the accuracy? (a) correct bad labels (b) work out the accuracy
- 10.📋 Planning an AI project: which comes first — choose what to sort or improve data, retest? (a) choose what to sort (b) improve data, retest
- 11.📦 Tara collected 190 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 12.📋 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
- 13.⚖️ Two spam spotter models were tested on the same 50 messages. Model A got 40 right and Model B got 33 right. How many percentage points more accurate is Model A?
- 14.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a new colour screen (b) more labelled examples (c) fewer examples (d) a louder speaker
- 15.📋 Planning an AI project: which comes first — work out the accuracy or choose what to sort? (a) work out the accuracy (b) choose what to sort
- 16.🎯 Saanvi’s bird-song app is 90% accurate. If it is tested on 100 new bird songs, how many should it get right?
- 17.🎯 Vihaan’s spam spotter is 90% accurate. If it is tested on 100 new messages, how many should it get right?
- 18.📋 Planning an AI project: which comes first — split train and test or improve data, retest? (a) split train and test (b) improve data, retest
- 19.🧪 What is accuracy? (a) total − correct (b) correct + total (c) total × 2 (d) correct ÷ total × 100
- 20.📋 Planning an AI project: which comes first — split train and test or try unseen examples? (a) split train and test (b) try unseen examples
- 21.📋 Planning an AI project: which comes first — correct bad labels or fix it and test again? (a) correct bad labels (b) fix it and test again
- 22.🧪 Why must you test a model on examples it has NOT seen? (a) to save paper (b) to see if it learned (c) to make it faster (d) to make it bigger
- 23.📋 Planning an AI project: which comes first — split train and test or train the model? (a) split train and test (b) train the model
- 24.📋 Planning an AI project: which comes first — test on new photos or train the model? (a) test on new photos (b) train the model
- 25.❌ Nisha’s spam spotter was tested on 22 new messages and got 19 right. How many did it get wrong?
- 26.❌ Nisha’s recycling sorter was tested on 46 new waste photos and got 37 right. How many did it get wrong?
- 27.📦 Aarav collected 40 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 28.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 37 right and Model B got 26 right. How many percentage points more accurate is Model A?
- 29.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 45 right and Model B got 38 right. How many percentage points more accurate is Model A?
- 30.📋 Planning an AI project: which comes first — work out the accuracy or let it learn patterns? (a) work out the accuracy (b) let it learn patterns
- 31.🎯 Kabir’s leaf identifier was tested on 5 new leaf photos and got 5 right. What is its accuracy in percent?
- 32.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 20 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 33.📋 Planning an AI project: which comes first — work out the accuracy or recheck every label? (a) work out the accuracy (b) recheck every label
- 34.🎯 Saanvi’s handwriting reader was tested on 5 new handwritten letters and got 5 right. What is its accuracy in percent?
- 35.⚖️ Two recycling sorter models were tested on the same 25 waste photos. Model A got 21 right and Model B got 20 right. How many percentage points more accurate is Model A?
- 36.📋 Planning an AI project: which comes first — pick a question to solve or gather many examples? (a) pick a question to solve (b) gather many examples
- 37.🎯 Vihaan’s leaf identifier is 80% accurate. If it is tested on 40 new leaf photos, how many should it get right?
- 38.📦 Arjun collected 60 labelled fruit photos for a fruit sorter and keeps one fifth of them for testing. How many are left for training?
- 39.🎯 Kabir’s spam spotter is 80% accurate. If it is tested on 90 new messages, how many should it get right?
- 40.🎯 Ishaan’s spam spotter is 70% accurate. If it is tested on 20 new messages, how many should it get right?
Answer key
- choose what to sort
- 5
- paper and examples
- 68
- split train and test
- 64
- 8
- recheck every label
- correct bad labels
- choose what to sort
- 152
- calculate percent right
- 14
- more labelled examples
- choose what to sort
- 90
- 90
- split train and test
- correct ÷ total × 100
- split train and test
- correct bad labels
- to see if it learned
- split train and test
- train the model
- 3
- 9
- 32
- 22
- 14
- let it learn patterns
- 100
- 35
- recheck every label
- 100
- 4
- pick a question to solve
- 32
- 48
- 72
- 14
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students