Univariate Linear Regression

In supervised learning, we have a dataset also called a training set. the job is to learn from the data how to predict a continuous-valued output.

: Case 0.1:

Given a table of house prices and the respective sizes as our dataset

If we want to predict the price of a house given its size:

$1000 400sqm

$3000 5900sqm

…

Notation:

m = number of training examples (dataset, as per rows)

x’s = “input” variable/features (size of house)

y’s = “output” variable/”target” variable (price of house)

(x, y) —> Single datapoint (row)

(x^i, y^i) —> Specific training example ( ith training example), where i is the index.

How Supervised Learning Works

Start by feeding your dataset to the learning algorithm, it’s the job of the learning algorithm to then output a function which by convention is usually denoted h (meaning hypothesis). the job of the hypothesis is to take an input and predict a valued output.

size of house —> h —> Estimated price

h maps from x —> y

x = size of house

y = estimated price

Photo from Andrew NG ‘s ML class.

OnlyOnePixel

Machine Learning #3