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 — tag each photo by type or collect fruit photos? (a) tag each photo by type (b) collect fruit photos
- 2.🧪 You can plan a simple AI project with… (a) paper and examples (b) a secret password (c) only a big robot (d) nothing at all
- 3.📋 Planning an AI project: which comes first — try unseen examples or calculate percent right? (a) try unseen examples (b) calculate percent right
- 4.❌ Tara’s spam spotter was tested on 13 new messages and got 11 right. How many did it get wrong?
- 5.📋 Planning an AI project: which comes first — set aside test photos or label each example? (a) set aside test photos (b) label each example
- 6.⚖️ Two bird-song app models were tested on the same 25 bird songs. Model A got 19 right and Model B got 13 right. How many percentage points more accurate is Model A?
- 7.🎯 Diya’s fruit sorter was tested on 25 new fruit photos and got 18 right. What is its accuracy in percent?
- 8.📋 Planning an AI project: which comes first — improve data, retest or work out the accuracy? (a) improve data, retest (b) work out the accuracy
- 9.⚖️ Two leaf identifier models were tested on the same 25 leaf photos. Model A got 19 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 10.🧪 What is accuracy? (a) total × 2 (b) total − correct (c) correct + total (d) correct ÷ total × 100
- 11.📦 Vihaan collected 110 labelled handwritten letters for a handwriting reader and keeps one fifth of them for testing. How many are left for training?
- 12.❌ Arjun’s spam spotter was tested on 30 new messages and got 28 right. How many did it get wrong?
- 13.🧪 Why must you test a model on examples it has NOT seen? (a) to make it faster (b) to save paper (c) to see if it learned (d) to make it bigger
- 14.❌ Nisha’s recycling sorter was tested on 26 new waste photos and got 25 right. How many did it get wrong?
- 15.🧪 Your fruit sorter mixes up oranges and lemons. What helps most? (a) a new colour screen (b) fewer examples (c) a louder speaker (d) more labelled examples
- 16.📋 Planning an AI project: which comes first — calculate percent right or try unseen examples? (a) calculate percent right (b) try unseen examples
- 17.📋 Planning an AI project: which comes first — recheck every label or improve data, retest? (a) recheck every label (b) improve data, retest
- 18.🎯 Ananya’s handwriting reader is 60% accurate. If it is tested on 80 new handwritten letters, how many should it get right?
- 19.📋 Planning an AI project: which comes first — set aside test photos or work out the accuracy? (a) set aside test photos (b) work out the accuracy
- 20.📋 Planning an AI project: which comes first — try unseen examples or train the model? (a) try unseen examples (b) train the model
- 21.📋 Planning an AI project: which comes first — gather many examples or split train and test? (a) gather many examples (b) split train and test
- 22.🎯 Ananya’s leaf identifier is 50% accurate. If it is tested on 90 new leaf photos, how many should it get right?
- 23.⚖️ Two handwriting reader models were tested on the same 20 handwritten letters. Model A got 17 right and Model B got 15 right. How many percentage points more accurate is Model A?
- 24.📋 Planning an AI project: which comes first — collect fruit photos or label each example? (a) collect fruit photos (b) label each example
- 25.❌ Vihaan’s spam spotter was tested on 41 new messages and got 32 right. How many did it get wrong?
- 26.📋 Planning an AI project: which comes first — pick a question to solve or try unseen examples? (a) pick a question to solve (b) try unseen examples
- 27.🎯 Kabir’s spam spotter was tested on 4 new messages and got 3 right. What is its accuracy in percent?
- 28.📋 Planning an AI project: which comes first — work out the accuracy or train the model? (a) work out the accuracy (b) train the model
- 29.🎯 Rohan’s bird-song app is 90% accurate. If it is tested on 40 new bird songs, how many should it get right?
- 30.🎯 Saanvi’s handwriting reader is 50% accurate. If it is tested on 80 new handwritten letters, how many should it get right?
- 31.📦 Arjun collected 40 labelled waste photos for a recycling sorter and keeps one fifth of them for testing. How many are left for training?
- 32.⚖️ Two fruit sorter models were tested on the same 20 fruit photos. Model A got 20 right and Model B got 18 right. How many percentage points more accurate is Model A?
- 33.📋 Planning an AI project: which comes first — train the model or label each example? (a) train the model (b) label each example
- 34.📋 Planning an AI project: which comes first — work out the accuracy or correct bad labels? (a) work out the accuracy (b) correct bad labels
- 35.🎯 Aarav’s fruit sorter is 50% accurate. If it is tested on 30 new fruit photos, how many should it get right?
- 36.📦 Diya collected 170 labelled messages for a spam spotter and keeps one fifth of them for testing. How many are left for training?
- 37.📋 Planning an AI project: which comes first — fix it and test again or work out the accuracy? (a) fix it and test again (b) work out the accuracy
- 38.📋 Planning an AI project: which comes first — gather many examples or correct bad labels? (a) gather many examples (b) correct bad labels
- 39.📦 Aarav collected 90 labelled bird songs for a bird-song app and keeps one fifth of them for testing. How many are left for training?
- 40.📋 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
Answer key
- collect fruit photos
- paper and examples
- try unseen examples
- 2
- label each example
- 24
- 72
- work out the accuracy
- 4
- correct ÷ total × 100
- 88
- 2
- to see if it learned
- 1
- more labelled examples
- try unseen examples
- recheck every label
- 48
- set aside test photos
- train the model
- gather many examples
- 45
- 10
- collect fruit photos
- 9
- pick a question to solve
- 75
- train the model
- 36
- 40
- 32
- 10
- label each example
- correct bad labels
- 15
- 136
- work out the accuracy
- gather many examples
- 72
- calculate percent right
Free ai for students lessons, practice and worksheets at talentjr.in/ai-for-students