ML - Machine Learning Basics - Part 4

11. Probability

Probability is the chance of something happening.
Example: Tossing a coin → chance of heads is 50%.
In ML, probability is used for predictions like: “This email has 80% chance of being spam.”

12. Outliers

Outliers are unusual values that don’t fit with the rest of the data.
Example: Class test marks = [30, 35, 32, 95]. The student with 95 is very different from others — that’s an outlier.
Outliers can mislead ML models if not handled carefully.

13. Bias and Variance

Bias = error because the model is too simple.

Variance = error because the model is too complex and changes too much with data.
Example:

A student always guesses the same answer → high bias.

A student changes answers too often depending on random hints → high variance.
Good ML balances both.

14. Classification

Classification is when ML predicts categories instead of numbers.
Example: Is this fruit an apple, banana, or orange?
Or: Is this email spam or not spam?
It’s like sorting things into boxes.

Видео ML - Machine Learning Basics - Part 4 канала notesforimpact