← all demos
Computer & Data Science

Learning Curve

E(n) = a + b·e^(−n/τ)
Learning Curve

Training and validation error falling as more data arrives: the gap between the two curves is the generalization gap that shrinks but never fully closes.

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).