omnibias — scientific ML notebooks and engineeringhttps://omnibias.aiReproducible scientific machine learning workflows from Derivon and omnibias.enA fourth-order beam PINN in PyTorchhttps://omnibias.ai/docs/notebooks/beam-pinn/https://omnibias.ai/docs/notebooks/beam-pinn/Solve a clamped Euler–Bernoulli beam with a nonuniform load, forward Taylor jets, exact boundary conditions, and independent solution checks.Mon, 05 Oct 2026 00:00:00 +0400A Poisson PINN without a full Hessianhttps://omnibias.ai/docs/notebooks/poisson-pinn/https://omnibias.ai/docs/notebooks/poisson-pinn/Train a two-dimensional Poisson PINN using direct Laplacian contraction, then inspect solution error, boundary error, and residual error separately.Mon, 05 Oct 2026 00:00:00 +0400Train differentiable regions and local expertshttps://omnibias.ai/docs/notebooks/regional-regression/https://omnibias.ai/docs/notebooks/regional-regression/Learn a soft split and two regional regressors together, validate held-out predictions, and measure what changes when routing is hardened.Mon, 05 Oct 2026 00:00:00 +0400Calibrate a scientific model with Gauss–Newtonhttps://omnibias.ai/docs/notebooks/decay-calibration/https://omnibias.ai/docs/notebooks/decay-calibration/Recover amplitude, decay rate, and offset in a nonlinear least-squares inverse problem using a verified residual Jacobian and functional Gauss–Newton steps.Mon, 05 Oct 2026 00:00:00 +0400