Skip to main content
API REFERENCE/omnibias-jax

omnibias.jax.architectures

0.5.0rc1Release candidatePython >=3.10Apache-2.0

JAX activation derivatives, functional network jets, direct contractions, and parameter-differentiable numerical models.

import omnibias.jax.architectures
Module contract & mathematical conventions

Reusable PINN architectures over the shared activation derivative tower.

Includes multilayer and Fourier-feature fields, multiscale fields, hard boundary constraints, attention jets, integral kernels, and residual networks.

Shared formulas do not imply universal floating-point identity. Verify dtype, shape, derivative-order support, and the stated numerical assumptions for the path you use.

Module source ↗Source revision 9a2d73df0573Running reference examples →
attentionModule ↗ftc_netModule ↗hardbcModule ↗integral_kernelModule ↗jetkanModule ↗multiscaleModule ↗pinnModule ↗piratenetModule ↗

Imports & aliases​

These names share a definition with another public module. Follow a name for its full contract, parameters, and examples.

Import from this moduleCanonical reference
AdaptiveActivationomnibias.jax.architectures.AdaptiveActivation
AdaptiveJetMLPomnibias.jax.architectures.AdaptiveJetMLP
AffineFactoromnibias.jax.architectures.AffineFactor
AffineLiftomnibias.jax.architectures.AffineLift
AttentionJetMLPomnibias.jax.architectures.AttentionJetMLP
BoundaryMaskomnibias.jax.architectures.BoundaryMask
DualFTCConfigomnibias.core.ftc.DualFTCConfig
FTCNetomnibias.jax.architectures.FTCNet
FTCNetConfigomnibias.core.ftc.FTCNetConfig
FourierFeatureMLPomnibias.jax.architectures.FourierFeatureMLP
HardConstraintFieldomnibias.jax.architectures.HardConstraintField
IntegralKernelConfigomnibias.core.integral_kernel.IntegralKernelConfig
JetKANConfigomnibias.jax.architectures.JetKANConfig
JetKANParamsomnibias.jax.architectures.JetKANParams
JetMLPomnibias.jax.architectures.JetMLP
MscaleMLPomnibias.jax.architectures.MscaleMLP
PirateNetConfigomnibias.jax.architectures.PirateNetConfig
dirichlet_intervalomnibias.jax.architectures.dirichlet_interval
dual_ftc_lossomnibias.jax.architectures.dual_ftc_loss
ftc_blockomnibias.jax.architectures.ftc_block
homogeneous_boxomnibias.jax.architectures.homogeneous_box
init_jet_kanomnibias.jax.architectures.init_jet_kan
init_pirate_paramsomnibias.jax.architectures.init_pirate_params
initial_valueomnibias.jax.architectures.initial_value
integral_kernel_applyomnibias.jax.architectures.integral_kernel_apply
jet_kan_applyomnibias.jax.architectures.jet_kan_apply
jet_kan_from_torch_stateomnibias.jax.architectures.jet_kan_from_torch_state
jet_kan_jetomnibias.jax.architectures.jet_kan_jet
jet_kan_jet_mvomnibias.jax.architectures.jet_kan_jet_mv
jetkan_from_band_planomnibias.jax.architectures.jetkan_from_band_plan
make_adaptive_activationomnibias.jax.architectures.make_adaptive_activation
make_adaptive_jet_mlpomnibias.jax.architectures.make_adaptive_jet_mlp
make_attention_jet_mlpomnibias.jax.architectures.make_attention_jet_mlp
make_fourier_feature_mlpomnibias.jax.architectures.make_fourier_feature_mlp
make_jet_mlpomnibias.jax.architectures.make_jet_mlp
make_mscale_mlpomnibias.jax.architectures.make_mscale_mlp
make_sirenomnibias.jax.architectures.make_siren
pirate_applyomnibias.jax.architectures.pirate_apply
pirate_featuresomnibias.jax.architectures.pirate_features
refine_packomnibias.jax.architectures.refine_pack
← Package overviewRunnable learning examples →