Tag: Deep Learning
-
Attention Is All You Need, Dissected: The 2017 Figure, Box by Box
Attention Is All You Need, read box by box: the two towers, three attention blocks, cross-attention, post-norm, and what modern models kept…
-
The Calculus Behind Backpropagation: Every Derivative, From First Principles
The calculus behind backpropagation, derived from first principles: the nudge ratio, the power rule, the chain rule, partial derivatives, and the fan-out…
-
How Neural Networks Learn: From One Neuron to Backpropagation, Concept by Concept
How do neural networks learn? Build it from scratch, concept by concept — from a single neuron to weighted sums, ReLU, loss,…