Skip to main content
API REFERENCE/omnibias-keras

omnibias.keras.activations.classical

0.0.2a1AlphaPython >=3.10Apache-2.0

Keras 3 operator layers and activation paths implemented with keras.ops for TensorFlow, JAX, or Torch.

import omnibias.keras.activations.classical
Module contract & mathematical conventions

Classical activations: exp, relu, silu, gelu.

Mirrors omnibias.torch.activations.classical on keras.ops. exp / silu / gelu have exact all-orders fast paths (silu / gelu via Leibniz on the analytic z*f(z) product, reusing the sigmoid / Gaussian-Hermite towers); relu is closed form to all orders on the almost-everywhere / regular-part convention (n >= 2 -> 0; singular delta at the kink dropped).

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 →
CONSTANT

EXP​

omnibias.keras.activations.classical.EXPSource ↗
EXP = register_activation(ActivationSpec(name='exp', forward=_exp_forward, derivative=_exp_forward, fastpath=_exp_fastpath, integral=_exp_forward, riccati_polynomial=(0.0, 1.0), noise_model='poisson', operator_role='K=2 collapse -> exp(z) (eigenfunction of d/dz); log-link Newton step for Poisson regression.'))

This exported constant is defined by the expression above. Its exact value and annotation come from the pinned source; use it with the module contract.

Read the implementation
EXP = register_activation(
    ActivationSpec(
        name="exp",
        forward=_exp_forward,
        derivative=_exp_forward,
        fastpath=_exp_fastpath,
        integral=_exp_forward,
        riccati_polynomial=(0.0, 1.0),
        noise_model="poisson",
        operator_role=(
            "K=2 collapse -> exp(z) (eigenfunction of d/dz); "
            "log-link Newton step for Poisson regression."
        ),
    )
)
Related APIsomnibias.core.ActivationSpec↗omnibias.keras.register_activation↗
CONSTANT

GELU​

omnibias.keras.activations.classical.GELUSource ↗
GELU = register_activation(ActivationSpec(name='gelu', forward=_gelu_forward, derivative=_gelu_derivative, fastpath=_gelu_fastpath, integral=_gelu_integral, riccati_polynomial=None, noise_model='none', operator_role='K=2 collapse -> Phi(z) + z * phi(z); smoothed half-space gate, transformer FFN compatibility.'))

This exported constant is defined by the expression above. Its exact value and annotation come from the pinned source; use it with the module contract.

Read the implementation
GELU = register_activation(
    ActivationSpec(
        name="gelu",
        forward=_gelu_forward,
        derivative=_gelu_derivative,
        fastpath=_gelu_fastpath,
        integral=_gelu_integral,
        riccati_polynomial=None,
        noise_model="none",
        operator_role=(
            "K=2 collapse -> Phi(z) + z * phi(z); "
            "smoothed half-space gate, transformer FFN compatibility."
        ),
    )
)
Related APIsomnibias.core.ActivationSpec↗omnibias.keras.register_activation↗
CONSTANT

RELU​

omnibias.keras.activations.classical.RELUSource ↗
RELU = register_activation(ActivationSpec(name='relu', forward=_relu_forward, derivative=_relu_derivative, fastpath=_relu_fastpath, integral=_relu_integral, riccati_polynomial=None, noise_model='none', operator_role='K=2 collapse -> Heaviside step; equality-constraint indicator, Moore-Penrose pseudoinverse limit.'))

This exported constant is defined by the expression above. Its exact value and annotation come from the pinned source; use it with the module contract.

Read the implementation
RELU = register_activation(
    ActivationSpec(
        name="relu",
        forward=_relu_forward,
        derivative=_relu_derivative,
        fastpath=_relu_fastpath,
        integral=_relu_integral,
        riccati_polynomial=None,
        noise_model="none",
        operator_role=(
            "K=2 collapse -> Heaviside step; equality-constraint indicator, "
            "Moore-Penrose pseudoinverse limit."
        ),
    )
)
Related APIsomnibias.core.ActivationSpec↗omnibias.keras.register_activation↗
CONSTANT

SILU​

omnibias.keras.activations.classical.SILUSource ↗
SILU = register_activation(ActivationSpec(name='silu', forward=_silu_forward, derivative=_silu_derivative, fastpath=_silu_fastpath, riccati_polynomial=None, noise_model='none', operator_role='K=2 collapse -> sigmoid + z * sigmoid * (1 - sigmoid); smoothed gate for transformer FFN compatibility.', aliases=('swish',)))

This exported constant is defined by the expression above. Its exact value and annotation come from the pinned source; use it with the module contract.

Read the implementation
SILU = register_activation(
    ActivationSpec(
        name="silu",
        forward=_silu_forward,
        derivative=_silu_derivative,
        fastpath=_silu_fastpath,
        riccati_polynomial=None,
        noise_model="none",
        operator_role=(
            "K=2 collapse -> sigmoid + z * sigmoid * (1 - sigmoid); "
            "smoothed gate for transformer FFN compatibility."
        ),
        aliases=("swish",),
    )
)
Related APIsomnibias.core.ActivationSpec↗omnibias.keras.register_activation↗
← Package overviewRunnable learning examples →