Computer Science
Grade 9
20 min
Machine Learning Basics
Machine Learning Basics
Tutorial Preview
1
Introduction & Learning Objectives
Learning Objectives
Define Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) and describe their relationship.
Differentiate between rule-based systems and learning-based systems.
Identify at least three real-world applications of AI and ML in their daily lives.
Explain the critical role of data in training a machine learning model.
Describe the basic steps of the machine learning process: data collection, model training, and prediction.
Distinguish between the three main types of machine learning: supervised, unsupervised, and reinforcement learning.
Ever wonder how your phone knows what you're about to type, or how Netflix suggests the perfect movie? 🤖 That's AI at work!
In this lesson, we'll pull back the curtain on Artificial Int...
2
Key Concepts & Vocabulary
TermDefinitionExample
Artificial Intelligence (AI)The broad field of computer science focused on creating smart machines that can perform tasks that typically require human intelligence, like understanding language, recognizing images, and making decisions.A chess-playing computer that analyzes the board and chooses the best move to beat a human opponent.
Machine Learning (ML)A subfield of AI where computers learn patterns from data without being explicitly programmed for every single task. Instead of writing rules, we let the machine discover the rules itself.An email spam filter learns to identify junk mail by looking at thousands of examples of spam and non-spam emails.
DataThe information (like numbers, text, images, or sounds) that is collected and used to train a machine learning mo...
3
Core Syntax & Patterns
The AI Hierarchy
AI > ML > Deep Learning
Use this to understand how these popular terms relate. AI is the big idea of smart machines. Machine Learning (ML) is one way to achieve AI (by learning from data). Deep Learning is a very powerful technique within ML that uses complex structures called neural networks.
The Machine Learning Process
1. Collect Data -> 2. Train Model -> 3. Make Predictions
This is the fundamental workflow for almost any machine learning project. You can't have a smart model without first collecting good data, then using that data to train the model, which can then be used to make useful predictions.
Rule-Based vs. Learning-Based
Rule-Based: `if (condition) then (action)`. Learning-Based: `model.predict(data)`.
Traditional progra...
4 more steps in this tutorial
Sign up free to access the complete tutorial with worked examples and practice.
Sign Up Free to ContinueSample Practice Questions
Challenging
A team builds a model to predict stock prices. It performs with 99% accuracy on the historical data it was trained on, but when they use it on the current day's stock market, its predictions are completely wrong. Based on the tutorial's concepts, what is the most likely issue?
A.The team used Machine Learning, but they should have used a rule-based system.
B.The model has 'over-learned' the specific patterns of the training data and cannot generalize to new, unseen data.
C.The computer used for training was too slow.
D.The team did not collect enough data; they should have used less data to make it simpler.
Challenging
A smart thermostat company claims it uses 'AI' to learn your daily schedule and adjust the temperature automatically. Based on the AI hierarchy and the system's behavior of learning from your adjustments (data), what is the most precise description of the technology being used?
A.It is a simple rule-based system, not AI at all.
B.It is using Machine Learning (a subfield of AI) to learn patterns from user data over time.
C.It is using general AI that thinks and reasons exactly like a human.
D.It is using Deep Learning, which is more advanced than AI.
Challenging
A fellow student claims, 'We don't need to worry about collecting lots of data to identify spam emails. We can just design a really clever algorithm, and it will figure it out from a few examples.' Why does this statement show a misunderstanding of the core principles in the tutorial?
A.The statement is correct; a powerful algorithm is more important than the amount of data.
B.It's a misunderstanding because machine learning models' performance is critically dependent on the quality and quantity of data they are trained on.
C.It's a misunderstanding because only rule-based systems can identify spam, not learning-based ones.
D.The statement is correct, but only for unsupervised learning, not supervised learning.
Want to practice and check your answers?
Sign up to access all questions with instant feedback, explanations, and progress tracking.
Start Practicing Free