topic 01

linear regression

the workhorse. lines, residuals, and why least squares.

status · just started

tl;dr

one paragraph, your own words. if you can't write this from scratch, you don't get it yet.

intuition

how would you explain this to a friend over coffee? no notation, just the shape of the idea. what is the model actually trying to do? what does it assume about the world?

the math

key equation(s), what each symbol means, and a derivation sketch if it helps.

\hat{y} = \beta_0 + \beta_1 x \quad\quad \text{minimise: } \sum_i (y_i - \hat{y}_i)^2

(rendered as plain text for now — drop in KaTeX or MathJax later if you want pretty math.)

see it move

drop a gif or short video here that animates the concept.

gif / video goes here

replace the placeholder div with <img src="assets/your-gif.gif"> or a <video autoplay muted loop playsinline>.

code

smallest working example, well commented.

from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array([[1], [2], [3], [4]])
y = np.array([2, 4, 6, 8])

model = LinearRegression().fit(X, y)
print(model.coef_, model.intercept_)

what tripped me up

the thing the textbook glossed over
the bug that took two days to find
the assumption you didn't realise you were making

sources

the book / course chapter
the blog post that made it click
the paper, if any