Notes
A mixed notebook for blog-style build logs, AI course notes, visual explanations, and compact cheat sheets.
Sheaf Neural Networks, klasik GNN’lerin komşu bilgilerini aynı uzayda birleştirme varsayımını sorgular. Bu yazı; yerel bilgi uzayları, restriction map’ler ve Sheaf Laplacian üzerinden heterojen grafiklerde daha esnek bilgi aktarımını inceliyor.
Whisper becomes more useful when transcription is treated as one stage in a larger NLP system.
A confidence selector can turn deep and classical visual odometry branches into a more robust research architecture.
The fastest pipeline improvement is often moving repeated Python-level work into vectorized array operations.
Separating sale occurrence from sale magnitude can make sparse forecasting systems easier to reason about.
WAPE is useful, but sparse demand and high zero ratios can hide important failure modes.
A practical note on preserving temporal integrity when lagged features depend on previous predictions.