Posts
-
Temporal difference learning
-
Floyd's cycle finding algorithm
-
Conjugate Gradients
-
Automatic differentiation
-
Attention from Scratch in Julia
-
Backpropagation with Attention Components
-
Why mean squared error loss works poorly with softmax.
-
Python vs Julia Cheatsheet
-
Discrete Cosine Transform - Part 2
-
Discrete Cosine Transform - Part 1
-
Understanding Regularization