omnibias.keras.fastpath
Keras 3 operator layers and activation paths implemented with keras.ops for TensorFlow, JAX, or Torch.
import omnibias.keras.fastpathModule contract & mathematical conventions
Closed-form derivative / integral fast paths for the Keras backend.
Every kernel is written against keras.ops and shares its polynomial
coefficients with the torch and JAX backends via
omnibias.core.polynomials.
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.
Imports & aliases
These names share a definition with another public module. Follow a name for its full contract, parameters, and examples.
| Import from this module | Canonical reference |
|---|---|
gaussian_forward | omnibias.keras.fastpath.gaussian_forward |
gaussian_nth_derivative | omnibias.keras.fastpath.gaussian_nth_derivative |
hermite_coeffs | omnibias.core.hermite_coeffs |
multibias_collapsed_forward | omnibias.keras.fastpath.multibias_collapsed_forward |
multibias_integral_forward | omnibias.keras.fastpath.multibias_integral_forward |
multibias_integral_window_forward | omnibias.keras.fastpath.multibias_integral_window_forward |
multibias_literal_forward | omnibias.keras.fastpath.multibias_literal_forward |
sigmoid_nth_derivative | omnibias.keras.fastpath.sigmoid_nth_derivative |
sigmoid_polynomial_coeffs | omnibias.core.sigmoid_polynomial_coeffs |
softplus_nth_derivative | omnibias.keras.fastpath.softplus_nth_derivative |
tanh_nth_derivative | omnibias.keras.fastpath.tanh_nth_derivative |
tanh_polynomial_coeffs | omnibias.core.tanh_polynomial_coeffs |