<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/cross-entropy-loss</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/information-theory-foundations</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/defining-cross-entropy</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/cross-entropy-and-perplexity</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/bits-per-character</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/binary-vs-categorical-cross-entropy</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/gradient-behavior-and-why-cross-entropy-works</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/training-dynamics-and-loss-curves</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/worked-example</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/code-implementation</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/numerical-stability-in-practice</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/implementation-parameters</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/limitations-and-impact</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/summary</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/cross-entropy-loss-language-models-information-theory/quiz</loc><lastmod>2026-02-21T14:30:00.000Z</lastmod></url></urlset>