https://anooj.bearblog.dev/ 2026-01-30 https://anooj.bearblog.dev/bdt-1/ 2026-02-12 https://anooj.bearblog.dev/unfolding-attention/ 2026-02-12 https://anooj.bearblog.dev/rethinking-attention-with-approx-semirings/ 2025-11-18 https://anooj.bearblog.dev/weight-init-variance-of-nns/ 2026-01-30 https://anooj.bearblog.dev/derivations-of-gradients-wrt-neural-networks/ 2025-11-20