Understanding machine learning terminology
As you’ve already learned, machine learning is another way to think about predicting outcomes based on observed data sets.
Machine learning models are essentially software applications that use mathematical functions to calculate output values based on input values. This process involves two main phases: training and inferencing.
Training
During training, the model learns to predict output values based on input values by analyzing past observations. These past observations include both the features (input values) and labels (output values).
In a typical scenario, features are represented as variables denoted by x, while labels are denoted by y. Features can consist of multiple values, forming a vector represented by [x1, x2, x3, ...],y. For example, in predicting bottled water sales based on weather, weather measurements are features (x) and the number of bottles sold is the label (y).
An algorithm is then applied to...
