The Unreasonable Effectiveness of Stochastic Gradient Descent (in 3 minutes)
3:18
Accelerate Gradient Descent with Momentum (in 3 minutes)
3:06
Gradient Descent in 3 minutes
10:53
Stochastic Gradient Descent, Clearly Explained!!!
25:28
Watching Neural Networks Learn
15:52
Optimization for Deep Learning (Momentum, RMSprop, AdaGrad, Adam)
27:14
Transformers (how LLMs work) explained visually | DL5
40:08
The Most Important Algorithm in Machine Learning
3:18