The Hypothesis Function

 

Our hypothesis function has the general form:

y^=hθ(x)=θ0+θ1x\hat{y} = h_\theta(x) = \theta_0 + \theta_1 x

The hypothesis function hθ(x)h_\theta(x) is sometimes simply denoted as h(x)h(x).

Note that this is like the equation of a straight line. We give to hθ(x)h_\theta(x) values for θ0\theta_0 and θ1\theta_1 to get our estimated output y^\hat{y}.

We try to find proper values for θ0\theta_0 and θ1\theta_1 which provide the best possible "fit" or the most representative "straight line" through the data points mapped on the x-y plane.

A list of m training examples — (x(i),y(i));i=1,...,m(x^{(i)},y^{(i)}); i=1,...,m — is called a training set. Our goal is, given a training set, to learn a hypothesis function h : X → Y so that h(x) is a “good” predictor for the corresponding value of y.

We will also use X to denote the space of input values, and Y to denote the space of output values. In this example, X=Y=RX = Y = \mathbb{R}.

01-supervised-learning