How AI Systems Work – Practical Foundations for Modern Learners
Lesson 5: Learning from Examples
Lesson Objectives
By the end of this lesson, students should be able to:
- Explain supervised learning in plain language.
- Distinguish training examples from real-world understanding.
- Recognize overfitting as learning the wrong lesson from examples.
Lesson Content
Machine learning usually means improving performance from experience. In supervised learning, the system studies examples that include inputs and correct outputs. After training, it tries to predict the right output for a new input.
This is powerful, but it is not the same as wisdom. If the examples are narrow, biased, mislabeled, stale, or missing important cases, the system can learn patterns that fail outside the training set.
Overfitting happens when a system becomes too attached to the training examples. Imagine a student who memorizes practice questions but cannot solve a slightly different problem. The student did not learn the idea; the student learned the surface pattern.
Enroll to continue this lesson.
The preview above shows the lesson objectives and opening lesson content. Enroll to view the full lesson, complete the practice work, and take the lesson quiz.