March 26, 2026 CNN Regression on Rendered Meshes: What Improved It Getting a feature detector from terrible to useful: data leakage, camera projection, horizontal mirroring, memory management, and a second-layer MLP for 3D.
machine-learningcnnmlptensorflowkeraspythonthree.jscomputer-vision
Read article
March 19, 2026 The Dot Product Is All You Need Every neural network, every embedding, every attention head reduces to the same operation: multiply and sum. How the dot product encodes meaning in high-dimensional space.
machine-learningmathematicsnlptransformers
Read article
March 16, 2026 Attention Is All You Need: Building the Original Transformer that Started the LLM Revolution Attention Is All You Need replaced RNNs with self-attention and changed everything. I built the original encoder-decoder transformer from scratch and trained it to translate English to French.
machine-learningpythonpytorchnlptransformers
Read article
March 14, 2026 Building a Tiny LLM From Scratch, Trained on Poe A decoder-only transformer, two tokenizers, and 1.9 million characters of Edgar Allan Poe. What building an LLM from zero teaches you.
machine-learningpythonpytorchnlptransformers
Read article