Computer & Data Science
Binary Cross-Entropy Loss
L = −[y ln p + (1−y) ln(1−p)]
The log-loss penalty for a probabilistic prediction, drawn here for a mixed target: it is gentle near a confident correct answer but climbs steeply as the prediction heads to either wrong extreme.
Computed & rendered in pure C# on the frozen OnlyCSharp 1.8 library — animation baked to GIF with the library's own
Gif encoder (no GPU, no ffmpeg, no external packages).