7:40GELU: The Activation Function That Powers Modern AI like BERT and GPTSH AI Academy1.5K viewsView & Download
11:02A shallow grip on neural networks (What is the "universal approximation theorem"?)Sheafification of G22.8K viewsView & Download
15:40[Part 1] Using Generating Functions to Solve Non-Homogeneous Recurrence RelationsAlex's World of Math118 viewsView & Download