The simple understanding is: this formula represents the amount of each reduction ( as a gradient), and when it is reduced until the difference between the two iterations is small enough, the minimum value of the loss function J is obtained.
3. Machine Learning Algorithm Learning --- Gradient Descent (6-1 and 6-2 What is Gradient Descent)
Guess you like
Origin http://43.154.161.224:23101/article/api/json?id=324519122&siteId=291194637
Recommended
Ranking