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.🧪 Why must you test a model on examples it has NOT seen? (a) to see if it learned (b) to make it bigger (c) to save paper (d) to make it faster
- 2.🧪 You can plan a simple AI project with… (a) a secret password (b) only a big robot (c) nothing at all (d) paper and examples
- 3.📋 Planning an AI project: which comes first — calculate percent right or improve data, retest? (a) calculate percent right (b) improve data, retest
- 4.📦 Meera collected 90 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 5.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 6.📋 Planning an AI project: which comes first — choose what to sort or recheck every label? (a) choose what to sort (b) recheck every label
- 7.🎯 Arjun’s leaf identifier is 60% accurate. If it is tested on 90 new leaf photos, how many should it get right?
- 8.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) more labelled examples (b) a louder speaker (c) a new colour screen (d) fewer examples
- 9.❌ Tara’s leaf identifier was tested on 38 new leaf photos and got 33 right. How many did it get wrong?
- 10.📋 Planning an AI project: which comes first — split train and test or correct bad labels? (a) split train and test (b) correct bad labels
- 11.⚖️ Two handwriting reader models were tested on the same 25 handwritten letters. Model A got 17 right and Model B got 14 right. How many percentage points more accurate is Model A?
- 12.🎯 Saanvi’s bird-song app is 80% accurate. If it is tested on 60 new bird songs, how many should it get right?
- 13.❌ Meera’s fruit sorter was tested on 28 new fruit photos and got 24 right. How many did it get wrong?
- 14.🎯 Kabir’s leaf identifier was tested on 4 new leaf photos and got 4 right. What is its accuracy in percent?
- 15.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 17 right and Model B got 12 right. How many percentage points more accurate is Model A?
- 16.📋 Planning an AI project: which comes first — let it learn patterns or recheck every label? (a) let it learn patterns (b) recheck every label
- 17.🎯 Arjun’s leaf identifier is 60% accurate. If it is tested on 100 new leaf photos, how many should it get right?
- 18.🎯 Aarav’s handwriting reader is 60% accurate. If it is tested on 40 new handwritten letters, how many should it get right?
- 19.📋 Planning an AI project: which comes first — work out the accuracy or try unseen examples? (a) work out the accuracy (b) try unseen examples
- 20.❌ Vihaan’s leaf identifier was tested on 41 new leaf photos and got 38 right. How many did it get wrong?
- 21.📋 Planning an AI project: which comes first — let it learn patterns or choose what to sort? (a) let it learn patterns (b) choose what to sort
- 22.📋 Planning an AI project: which comes first — label each example or choose what to sort? (a) label each example (b) choose what to sort
- 23.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 14 right and Model B got 12 right. How many percentage points more accurate is Model A?
- 24.📦 Tara collected 50 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 25.❌ Arjun’s leaf identifier was tested on 38 new leaf photos and got 30 right. How many did it get wrong?
- 26.📋 Planning an AI project: which comes first — work out the accuracy or pick a question to solve? (a) work out the accuracy (b) pick a question to solve
- 27.🎯 Tara’s leaf identifier was tested on 25 new leaf photos and got 13 right. What is its accuracy in percent?
- 28.📋 Planning an AI project: which comes first — pick a question to solve or correct bad labels? (a) pick a question to solve (b) correct bad labels
- 29.⚖️ Two fruit sorter models were tested on the same 10 fruit photos. Model A got 10 right and Model B got 6 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.❌ Meera’s handwriting reader was tested on 46 new handwritten letters and got 37 right. How many did it get wrong?
- 32.🎯 Saanvi’s leaf identifier is 70% accurate. If it is tested on 20 new leaf photos, how many should it get right?
- 33.❌ Diya’s bird-song app was tested on 29 new bird songs and got 25 right. How many did it get wrong?
- 34.📋 Planning an AI project: which comes first — collect fruit photos or test on new photos? (a) collect fruit photos (b) test on new photos
- 35.⚖️ Two bird-song app models were tested on the same 20 bird songs. Model A got 16 right and Model B got 15 right. How many percentage points more accurate is Model A?
- 36.🎯 Arjun’s leaf identifier was tested on 4 new leaf photos and got 3 right. What is its accuracy in percent?
- 37.⚖️ Two bird-song app models were tested on the same 50 bird songs. Model A got 43 right and Model B got 26 right. How many percentage points more accurate is Model A?
- 38.📋 Planning an AI project: which comes first — let it learn patterns or work out the accuracy? (a) let it learn patterns (b) work out the accuracy
- 39.🎯 Aarav’s handwriting reader was tested on 10 new handwritten letters and got 7 right. What is its accuracy in percent?
- 40.🎯 Arjun’s fruit sorter is 90% accurate. If it is tested on 100 new fruit photos, how many should it get right?
Answer key
- to see if it learned
- paper and examples
- calculate percent right
- 72
- calculate percent right
- choose what to sort
- 54
- more labelled examples
- 5
- correct bad labels
- 12
- 48
- 4
- 100
- 25
- recheck every label
- 60
- 24
- try unseen examples
- 3
- choose what to sort
- choose what to sort
- 10
- 40
- 8
- pick a question to solve
- 52
- pick a question to solve
- 40
- let it learn patterns
- 9
- 14
- 4
- collect fruit photos
- 5
- 75
- 34
- let it learn patterns
- 70
- 90
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students