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 bird-song app models were tested on the same 10 bird songs. Model A got 10 right and Model B got 9 right. How many percentage points more accurate is Model A?
- 2.📋 Planning an AI project: which comes first — gather many examples or improve data, retest? (a) gather many examples (b) improve data, retest
- 3.🧪 What is accuracy? (a) total × 2 (b) total − correct (c) correct + total (d) correct ÷ total × 100
- 4.⚖️ Two leaf identifier models were tested on the same 50 leaf photos. Model A got 46 right and Model B got 40 right. How many percentage points more accurate is Model A?
- 5.🎯 Ananya’s spam spotter was tested on 50 new messages and got 44 right. What is its accuracy in percent?
- 6.⚖️ Two leaf identifier models were tested on the same 10 leaf photos. Model A got 10 right and Model B got 7 right. How many percentage points more accurate is Model A?
- 7.❌ Rohan’s leaf identifier was tested on 43 new leaf photos and got 34 right. How many did it get wrong?
- 8.🧪 Why must you test a model on examples it has NOT seen? (a) to make it bigger (b) to save paper (c) to make it faster (d) to see if it learned
- 9.❌ Saanvi’s fruit sorter was tested on 20 new fruit photos and got 17 right. How many did it get wrong?
- 10.📋 Planning an AI project: which comes first — calculate percent right or test on new photos? (a) calculate percent right (b) test on new photos
- 11.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) fewer examples (b) a louder speaker (c) a new colour screen (d) more labelled examples
- 12.📋 Planning an AI project: which comes first — set aside test photos or train the model? (a) set aside test photos (b) train the model
- 13.📋 Planning an AI project: which comes first — train the model or fix it and test again? (a) train the model (b) fix it and test again
- 14.🎯 Meera’s leaf identifier is 70% accurate. If it is tested on 90 new leaf photos, how many should it get right?
- 15.🎯 Ananya’s handwriting reader is 90% accurate. If it is tested on 80 new handwritten letters, how many should it get right?
- 16.📦 Diya collected 150 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 17.⚖️ Two spam spotter models were tested on the same 25 messages. Model A got 24 right and Model B got 23 right. How many percentage points more accurate is Model A?
- 18.🎯 Ishaan’s spam spotter is 50% accurate. If it is tested on 70 new messages, how many should it get right?
- 19.📋 Planning an AI project: which comes first — train the model or recheck every label? (a) train the model (b) recheck every label
- 20.📦 Arjun collected 190 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 21.📋 Planning an AI project: which comes first — split train and test or gather many examples? (a) split train and test (b) gather many examples
- 22.❌ Meera’s fruit sorter was tested on 41 new fruit photos and got 35 right. How many did it get wrong?
- 23.📋 Planning an AI project: which comes first — improve data, retest or calculate percent right? (a) improve data, retest (b) calculate percent right
- 24.📋 Planning an AI project: which comes first — tag each photo by type or train the model? (a) tag each photo by type (b) train the model
- 25.🧪 You can plan a simple AI project with… (a) nothing at all (b) only a big robot (c) a secret password (d) paper and examples
- 26.🎯 Aarav’s fruit sorter is 70% accurate. If it is tested on 80 new fruit photos, how many should it get right?
- 27.📋 Planning an AI project: which comes first — split train and test or correct bad labels? (a) split train and test (b) correct bad labels
- 28.📦 Kabir collected 190 labelled handwritten letters for a handwriting reader 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 train the model? (a) test on new photos (b) train the model
- 30.❌ Kabir’s leaf identifier was tested on 35 new leaf photos and got 33 right. How many did it get wrong?
- 31.⚖️ Two fruit sorter models were tested on the same 25 fruit photos. Model A got 17 right and Model B got 16 right. How many percentage points more accurate is Model A?
- 32.📦 Meera collected 170 labelled leaf photos for a leaf identifier and keeps one fifth of them for testing. How many are left for training?
- 33.📋 Planning an AI project: which comes first — collect fruit photos or fix it and test again? (a) collect fruit photos (b) fix it and test again
- 34.🎯 Arjun’s spam spotter was tested on 20 new messages and got 17 right. What is its accuracy in percent?
- 35.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
- 36.📋 Planning an AI project: which comes first — label each example or fix it and test again? (a) label each example (b) fix it and test again
- 37.🎯 Tara’s fruit sorter was tested on 25 new fruit photos and got 14 right. What is its accuracy in percent?
- 38.📋 Planning an AI project: which comes first — collect fruit photos or split train and test? (a) collect fruit photos (b) split train and test
- 39.⚖️ Two spam spotter models were tested on the same 20 messages. Model A got 14 right and Model B got 10 right. How many percentage points more accurate is Model A?
- 40.📋 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
Answer key
- 10
- gather many examples
- correct ÷ total × 100
- 12
- 88
- 30
- 9
- to see if it learned
- 3
- test on new photos
- more labelled examples
- set aside test photos
- train the model
- 63
- 72
- 120
- 4
- 35
- recheck every label
- 152
- gather many examples
- 6
- calculate percent right
- tag each photo by type
- paper and examples
- 56
- correct bad labels
- 152
- train the model
- 2
- 4
- 136
- collect fruit photos
- 85
- train the model
- label each example
- 56
- collect fruit photos
- 20
- test on new photos
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students