Deep Learning

Attention, transformers, convolutions and embeddings — worked out with real numbers instead of hand-waving.

Fundamentals Deep Learning Evaluation & Production

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.

Machine Learning Ai Python

9 min readAug 29, 2026vaibhavkothari

Advanced

The attention mechanism, worked out by hand

Queries, keys and values with real numbers. Why the scaling factor is sqrt(d_k), what multi-head attention buys, and how causal masking works.

Machine Learning Ai Python

9 min readAug 29, 2026vaibhavkothari

Advanced

Transformer from scratch in PyTorch, block by block

A working decoder-only transformer in 120 lines. Pre-norm, residual streams, why the MLP is 4x wide, weight tying, stable initialisation.

Machine Learning Ai Python

10 min readAug 29, 2026vaibhavkothari

Advanced

CNNs from scratch in NumPy: convolution as a matrix multiply

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.

Machine Learning Computer Vision Python

11 min readAug 29, 2026vaibhavkothari

Newsletter

Get new articles

Free essays on learning, Python, and ML — no account required. We’ll only email when there’s something worth reading.