Coursera Machine Learning Study notes (iv)



II. Linear Regression with one Variable (Week 1)

-Model representation

In the case of previous predictions of house prices, let's say that our training set of regression questions (Training set) looks like this:

We use the following notation to describe the amount of regression problems:

-M represents the number of instances in the training set

-X represents the feature/input variable

-Y represents the target variable/output variable

-(x, y) represents an instance of a training set

-Representing the first observation example

-H represents the solution or function of the learning algorithm, also known as hypothesis (hypothesis)

Therefore, to solve the problem of predicting house prices, the process is as follows:

We actually set the training to our learning algorithm and then learn to get a hypothetical H. After that, we will estimate the housing size of the house price as the input variable to H, and then predict the price as the output variable as the result.

Among them, what should be expressed about the hypothesis h in the problem of housing price forecast?

One possible way to express this is:

At the same time, because the problem contains only one feature/input variable, such a problem is called a univariate linear regression problem.

Coursera Machine Learning Study notes (iv)