Tag
matrix-multiplication
- Oct 18, 2024 The Fully Connected Layer as an Affine Map What a dense layer computes, why the weight matrix is transposed and the bias broadcast, and how the parameter count, the backward pass cost, and the collapse of stacked layers follow from one identity. deep learning
- Mar 24, 2023 Supersteps and Message Bounds: Why Distributed Parallelism Costs More How the BSP model charges for latency and bandwidth per round, what the h-relation says about all-to-all traffic, and why matrix multiplication needs more memory per processor to avoid moving data. algorithms