1 linear regression algorithm
Http://www.cnblogs.com/wangxin37/p/8297988.html
The term regression refers to the fact that we predict an accurate output value based on the previous data, for this example is the price, and there is another most common way to supervise learning, called classification, when we want to predict discrete output values, for example, we are looking for cancer tumors, and want to determine whether the tumour is benign or malignant , this is the problem of 0/1 discrete outputs. Further, in supervised learning we have a data set that is called the training set.
The tag we will use to describe this regression problem is as follows:
m m represents the number of instances in the training set
x x represents the feature/input variable
y y represents the target variable/output variable
(x,y) (x, y) represents an instance of a training set
(x (i) , y (i) (x (i), Y (i)) represent the Observation Example of I I
h h represents the solution or function of the learning algorithm also known as hypothesis (hypothesis)
This is how a supervised learning algorithm works, and we can see that there is a house price in our training set
We feed it to our learning algorithm, the learning algorithm works, and then output a function, usually denoted as lowercasehSaid.hRepresents hypothesis (assuming), H represents a function, the input is the size of the house, just like the house your friend wants to sell, sohh according to the inputxx value to deriveyY value,yThe Y value corresponds to the price of the house.hh is a x " >< Span id= "mathjax-span-317" class= "math" > x x to y " >< Span id= "mathjax-span-320" class= "math" > y y.
I will choose the initial usage rule hh for hypothesis, so to solve the housing price forecast problem, we are actually going to "feed" the training set to our learning algorithm, and then learn to get a hypothetical H, We then input the size of the house we want to predict as an input variable to H, predicting the price of the house's trade as output variable output as the result. So, how do we express H H for our house price forecasts ?
One possible way to express this is:hθ (x) =< Span id= "mathjax-span-339" class= "Msubsup" >θ0+ θ1x hθ (x) =θ0+θ1x, (H (x) =k*x+b) because only one feature/input variable is included, so the problem is called univariate linear regression.
Machine learning-linear regression algorithm (univariate) Linear Regression with one Variable