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.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a louder speaker (b) a new colour screen (c) more labelled examples (d) fewer examples
- 2.📋 Planning an AI project: which comes first — set aside test photos or try unseen examples? (a) set aside test photos (b) try unseen examples
- 3.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to make it bigger (c) to see if it learned (d) to save paper
- 4.🎯 Diya’s recycling sorter is 90% accurate. If it is tested on 20 new waste photos, how many should it get right?
- 5.⚖️ Two handwriting reader models were tested on the same 20 handwritten letters. Model A got 14 right and Model B got 11 right. How many percentage points more accurate is Model A?
- 6.📋 Planning an AI project: which comes first — fix it and test again or try unseen examples? (a) fix it and test again (b) try unseen examples
- 7.🎯 Kabir’s handwriting reader was tested on 4 new handwritten letters and got 4 right. What is its accuracy in percent?
- 8.📋 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
- 9.🎯 Saanvi’s bird-song app is 80% accurate. If it is tested on 60 new bird songs, how many should it get right?
- 10.🎯 Aarav’s recycling sorter is 50% accurate. If it is tested on 20 new waste photos, how many should it get right?
- 11.🧪 What is accuracy? (a) total × 2 (b) correct ÷ total × 100 (c) total − correct (d) correct + total
- 12.📦 Meera collected 80 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 13.❌ Vihaan’s leaf identifier was tested on 30 new leaf photos and got 23 right. How many did it get wrong?
- 14.❌ Diya’s leaf identifier was tested on 39 new leaf photos and got 38 right. How many did it get wrong?
- 15.📦 Kabir collected 110 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 16.⚖️ Two spam spotter models were tested on the same 25 messages. Model A got 25 right and Model B got 22 right. How many percentage points more accurate is Model A?
- 17.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 15 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 18.🎯 Kabir’s recycling sorter is 60% accurate. If it is tested on 50 new waste photos, how many should it get right?
- 19.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 9 right and Model B got 8 right. How many percentage points more accurate is Model A?
- 20.📋 Planning an AI project: which comes first — label each example or recheck every label? (a) label each example (b) recheck every label
- 21.📋 Planning an AI project: which comes first — try unseen examples or recheck every label? (a) try unseen examples (b) recheck every label
- 22.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 25 right and Model B got 20 right. How many percentage points more accurate is Model A?
- 23.📋 Planning an AI project: which comes first — work out the accuracy or improve data, retest? (a) work out the accuracy (b) improve data, retest
- 24.📦 Diya collected 120 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 25.📋 Planning an AI project: which comes first — test on new photos or work out the accuracy? (a) test on new photos (b) work out the accuracy
- 26.📋 Planning an AI project: which comes first — improve data, retest or collect fruit photos? (a) improve data, retest (b) collect fruit photos
- 27.📋 Planning an AI project: which comes first — label each example or pick a question to solve? (a) label each example (b) pick a question to solve
- 28.🧪 You can plan a simple AI project with… (a) nothing at all (b) paper and examples (c) only a big robot (d) a secret password
- 29.🎯 Arjun’s handwriting reader is 50% accurate. If it is tested on 10 new handwritten letters, how many should it get right?
- 30.📋 Planning an AI project: which comes first — improve data, retest or train the model? (a) improve data, retest (b) train the model
- 31.❌ Nisha’s handwriting reader was tested on 26 new handwritten letters and got 21 right. How many did it get wrong?
- 32.📋 Planning an AI project: which comes first — label each example or choose what to sort? (a) label each example (b) choose what to sort
- 33.❌ Aarav’s spam spotter was tested on 43 new messages and got 37 right. How many did it get wrong?
- 34.❌ Aarav’s handwriting reader was tested on 35 new handwritten letters and got 27 right. How many did it get wrong?
- 35.📦 Kabir collected 170 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 36.📋 Planning an AI project: which comes first — collect fruit photos or train the model? (a) collect fruit photos (b) train the model
- 37.📋 Planning an AI project: which comes first — improve data, retest or test on new photos? (a) improve data, retest (b) test on new photos
- 38.📋 Planning an AI project: which comes first — label each example or work out the accuracy? (a) label each example (b) work out the accuracy
- 39.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 24 right and Model B got 23 right. How many percentage points more accurate is Model A?
- 40.📦 Aarav collected 70 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
Answer key
- more labelled examples
- set aside test photos
- to see if it learned
- 18
- 15
- try unseen examples
- 100
- calculate percent right
- 48
- 10
- correct ÷ total × 100
- 64
- 7
- 1
- 88
- 12
- 10
- 30
- 10
- label each example
- recheck every label
- 20
- work out the accuracy
- 96
- test on new photos
- collect fruit photos
- pick a question to solve
- paper and examples
- 5
- train the model
- 5
- choose what to sort
- 6
- 8
- 136
- collect fruit photos
- test on new photos
- label each example
- 4
- 56
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students