Skip to content
All tags

#gradient-descent

2 posts
ai deep-dive 認識 AI 模型

How Models Improve Themselves: Gradient Descent and the Training Loop

A model uses loss to know how wrong it is and gradients to know which direction to adjust. Gradient descent repeats three things: compute loss, compute gradients, update parameters. The learning rate controls step size — too large and you overshoot, too small and training takes forever.

#gradient-descent#backpropagation#training#learning-rate#ai-model#optimization
ai deep-dive Reading CMU 07-280

CMU 07-280 Lecture 8: Gradient Descent, SGD, and Learning Rate

Lecture 8 moves from a one-dimensional parabola to vector gradients and compares batch GD, SGD, and mini-batches; the learning rate determines whether updates converge, oscillate, or diverge.

#cmu#ai-course#optimization#gradient-descent#machine-learning