Embeddings mathematically: what cosine similarity measures
The geometry of embedding space: why you normalise, what dimensionality really buys you, and the anisotropy problem nobody mentions.
Tag
Every article tagged Numpy. For a structured path, browse Learn.
The geometry of embedding space: why you normalise, what dimensionality really buys you, and the anisotropy problem nobody mentions.
Convolution forward and backward with no framework. The im2col trick that makes it fast, why the backward pass is a convolution too, and a net that trains.
Why A @ B and A * B give completely different answers, what "shapes not aligned" really means, and the one rule that makes matrix shapes click for good.
Your dataset is a matrix, a model is a matrix, and training is matrix multiplication repeated. Six operations, drawn out, with the ML job each one does.