notes/

builds/
  • jpeg compression/
  • karpathy 01 micrograd/
  • karpathy 02 bigram/
  • karpathy 03 mlp/
  • karpathy 04 batchnorm/
        • builds/
        • wiki/

              Builds

              Jul 07, 20261 min read

              Hands-on builds with annotated notebooks.

              Makemore — Andrej Karpathy

              9 notebooks
              Backprop & Autograd
              Scalar autograd engine, manual backprop, automated backward pass, and a minimal neural net library.
              5 notebooks + 2 helpers
              Bigram Language Model
              Character-level counting model, sampling, loss, smoothing, and an equivalent neural net.
              5 notebooks
              MLP / Makemore
              Scaling the bigram model to an MLP with embeddings, train/val/test splits, and experiments.
              1 notebook
              BatchNorm
              Training dynamics, activation statistics, gradient flow, initialization, and normalization.

              Algorithms

              1 notebook
              JPEG Compression
              Colour conversion, 8x8 DCT blocks, quantization, zig-zag scanning, RLE, and Huffman coding.

              Graph view

              • No backlinks found