Deep Learning

Paper Dissection: Understanding the Intrinsic Dimensionality of LLMs

Building mathematical intuition for why fine-tuning methods like LoRA work so well.

May 4 •

Beyond ‘training’: Dynamic Context Propagation in Keras!

Understanding 'training', and call-context argument propagation in Keras 3

May 1 •

Keras Internals: Debugging a Softmax Behavior Inconsistency

Exploring the Keras Softmax implementation details and fixing a subtle behavior inconsistency with masking.

Apr 12 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts