Syllabus Lesson 22 of 246 · Module 2: Maths and probability, only as needed
Module 2: Maths and probability, only as needed

Houses as lists of numbers (vectors)

Why it matters A network never sees a house, a word or a picture. It sees a list of numbers. Turning things into lists of numbers, and comparing those lists, is step one.

Describe a house by three numbers: size in tens of square metres, bedrooms, and distance to the station in km. House A is [8, 3, 1.5], house B is [9, 3, 2.0], house C is [4, 1, 6.0]. Each list is a vector: a point in a space with one direction per feature.

Tiny numbers

How different are A and B? Subtract feature by feature: [-1, 0, -0.5]. Square each: [1, 0, 0.25]. Add up: 1.25. Square root: about 1.12. That is the straight-line distance between the two points. A and C come out at about 6.34, so B is the closer match to A.

Vector: an ordered list of numbers, one per feature. Distance: the length of the straight line between two vectors, np.linalg.norm(a - b).

Recap Things become vectors; similar things become nearby points.

Words and symbols in this lesson
vector
a list of numbers, one per feature
Your turn

Write distance(a, b) (straight-line distance between two vectors, no loops) and most_similar(target, houses), which returns the index of the row in the 2D array houses closest to target.

Spotted a problem in this lesson? Report it · Ask about this lesson

This exercise opens soon

Finish the lesson before it and this one unlocks. The whole course is free, no account needed, and you can read this lesson right now.