How Do Machine Learning Models Learn? An Overview from Data Preparation to Training, Evaluation, and Prediction
When you start learning machine learning, you encounter many terms such as "features," "loss functions," "gradient descent," and "overfitting." Even if you look up the meaning of each, if you don't know where in the model-building process these terms are used, it becomes difficult to connect the knowledge. In this article, we will use a small example of supervised learning to organize the process from data preparation to training, evaluation, and prediction. First, we will grasp the overall flow and then place the basic terms within it. The target audience is those who have started learning machine learning or those who want to organize what each process in sample code is doing. By the end of this article, we aim for you to be able to explain the following three points: What is the model based on, and what is it adjusting? Why do we evaluate using data different from the training data?…
