اقْرَأْAmanahVale
Class 10
The Class 10 book

AI in Practice

6 units · 26 lessons · a project to end every unit, and one for the year

Open any lesson to read it the way a student does — one step at a time. Nothing you do here is saved; students work in their own accounts, where their missions, guesses and Checks are kept.

0
Unit 0

Refresher

1 lesson
  1. 0.1Back at the laptopLast year you got top marks for a model nobody ever tested. Was it any good?40 minVideo4 laptop missionsPictureDebateCheck · 5 questions
1
Unit 1

The project cycle, and ethical frameworks

5 lessons
  1. 1.1The cycle and the three domains, revisitedIt was 97% accurate. Then it marked Bilal absent three days running — while he sat at his desk.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  2. 1.2Frameworks, and what shapes a decisionYou give to the cause you can see from your desk. So does an AI trained on you.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  3. 1.3Types of ethical frameworksSpray 40 orchards out of 100. "Save the most apples" — or "save the most families"?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  4. 1.4Bioethics, and a hospital caseThe computer picked the man two streets from the hospital. It skipped the grandfather beyond the pass.40 minVideo4 laptop missionsPictureDebateCheck · 5 questions
  5. 1.5Applying a framework to our projectA kind idea, built to help children. Why did the team decide to stop?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  6. Unit projectThe ethics audit
2
Unit 2

Modelling

5 lessons
  1. 2.1AI, ML and DL, and the words for dataThe washing machine box says “AI”. Is it lying?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  2. 2.2Rule-based and learning-based; three ways to learnBilal's rule sorted 23 apples out of 36. Can a machine do better without being told any rule?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  3. 2.3Classification, regression, clustering, associationEvery samosa at break comes with a tea. Nobody told the canteen that — the receipts did.40 minVideo4 laptop missionsPictureDebateCheck · 5 questions
  4. 2.4Neural networks, and how AI makes a decisionSame sky, same forecast. Bilal goes to play cricket; Hiba stays home. Which of them is wrong?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  5. 2.5No-code AI: a model from statistical dataThe machine wrote its own rules for sorting apples. Can you read them — and should you trust them?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  6. Unit projectTeach a machine, explain its mind
3
Unit 3

Evaluating models

5 lessons
  1. 3.1Why evaluate, and the train-test splitThe leaf app scored 99% at the exhibition. In the orchard it was wrong again and again. Both were true.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  2. 3.2Accuracy and errorBilal built a leaf model in two seconds. It's 75% accurate. It has never caught a single scabbed leaf.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  3. 3.3The confusion matrix, from scratchWrong ten times can cost a farmer ₹3,000 — or ₹20,000. It depends which wrong.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  4. 3.4Precision, recall and F1A flood warning and a spam filter make opposite mistakes on purpose. Which one should never miss?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  5. 3.5Bias, transparency and accountability83% accurate — for everyone? Split the results by orchard and a different model appears.40 minVideo2 laptop missionsPictureDebateCheck · 5 questions
  6. Unit projectA report card for a model
4
Unit 4

Computer vision

5 lessons
  1. 4.1What computer vision doesYour phone read a signboard in Urdu and spoke it in English. What did it have to *see* first?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  2. 4.2Images are numbersThis sheet is 144 numbers. Colour them in and a picture appears. That's all a photo ever was.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  3. 4.3A no-code image classifierYour sorter is 100% right on the table. Move it to the floor and it falls apart. What did it really learn?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  4. 4.4Features and the convolution operatorNine numbers, slid across a picture, can find every edge in it. You'll do it by hand — then watch the apple light up.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  5. 4.5Inside a CNNTake your feature map from last lesson. Two formulas later you'll have built three layers of a real neural network.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  6. Unit projectFind the pictures that break it
5
Unit 5

Natural language processing

5 lessons
  1. 5.1Why language is hard, and the stages of NLP“His face turned red.” Angry? Embarrassed? Sunburnt? You knew at once. A machine has five stages to get through first.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  2. 5.2Chatbots: script bot and smart botAsk the school bot about the Eid holiday and it tells you about winter vacation — confidently. Why?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  3. 5.3Text normalisation“The TAP is broken!!!” and “the tap is broken” — to a computer, these share almost nothing. Until you clean them.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  4. 5.4Bag of words and TF-IDFFour slips from the suggestion box. Can a computer find the one word each slip is really about — without reading it?40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  5. 5.5Sentiment analysis“Not bad for the price.” Happy or unhappy? Your brain knew instantly. The computer got it backwards.40 minVideo3 laptop missionsPictureDebateCheck · 5 questions
  6. Unit projectA bot for a real job
Year projectBuild it, measure it, answer for itAll year you've learned to build models, measure them and question them. Now build one that matters — and stand up in front of the people it's for.