경사하강법

A mathematical technique to minimize loss. Gradient descent iteratively adjusts weights and biases, gradually finding the best combination to minimize loss. Gradient descent is older—much, much older—than machine learning.¹

Algorithm

The model begins training with randomized weights and biases near zero, and then repeats the following steps:²

1. Calculate the loss with the current weight and bias.
2. Determine the direction to move the weights and bias that reduce loss.
3. Move the weight and bias values a small amount in the direction that reduces loss.
4. Return to step one and repeat the process until it converges

Footnotes

1. developers.google.com/machine-learning/glossary#gradient_descent ↩

2. https://developers.google.com/machine-learning/crash-course/linear-regression/gradient-descent ↩