Machine LearningLesson 10Free preview

ML Training

This lesson is part of A.I. · All levels

Summary

Training is the process of training a model with data so that it can guess the correct output and correct the weight of the error. This process is repeated many times (epoch) with the learning rate that determines how much correction is done. The goal is to bridge the gap between prediction and reality to convergence.

Key points

Training makes models learn by adjusting weight based on error.
The learning rate sets the size of the weight correction step.
The learning rate is too high to make training convergent; too small to make it slow.
One epoch means one full iteration through the entire data training.
The goal of training is to minimize loss.

Full lesson

Code examples and quizzes

Full lessons, code examples, and quizzes are available to subscribers. 5 questions.