neural_tangents.stax.Hermite
- neural_tangents.stax.Hermite(degree)[source]
Hermite polynomials.
Inputs to this layer are assumed to have unit norm, i.e.
jnp.std(x, axis=channel_axis) == 1
. The Hermite polynomials are normalized so that the L2 norm w.r.t. standard Gaussian is 1.- Parameters:
degree (
int
) – a non-negative integer.- Return type:
- Returns:
(init_fn, apply_fn, kernel_fn)
.