Failed on benchmark
2025
Log-Scale Self-Similar Activation
Replace a conventional scalar activation by a geometrically indexed family of affine pieces whose slope changes with the logarithmic magnitude of the input. The same two endpoint parameters are reused across all scales, giving a compact, explicitly scale-aware activation that can represent different responses for exponentially separated activation magnitudes.
Paper: From two-dimensional continuous maps to one-dimensional discontinuous maps: a novel reduction explaining complex bifurcation structures in piecewise-linear families of maps
arXiv:2512.02291