The (very) Basics of Machine Learning Linear Regression

Linear regression is about predicting data by determining a line that predicts future y values for a given x value. Generally, the formula is:

   

where x is the input, c is the offset (known as the “bias”), and m is the slope/coefficient (called “weight”) of x. However, in machine learning, the above is typically written as:

   

Specifically:

y: the predicted label
b: the bias
w1: The weight, known in non-ML math as the slope
x1: A feature (known input)

The above model uses only one feature, but a more complex model may have multiple. For example: