netket.models.FastARNNConv1D

class netket.models.FastARNNConv1D

Bases: FastARNNSequential

Fast autoregressive neural network with 1D convolution layers.

See netket.models.FastARNNSequential for a brief explanation of fast autoregressive sampling.

Attributes

kernel_dilation: int = 1

1).

Type:

dilation factor of the convolution kernel (default

machine_pow: int = 2

exponent to normalize the outputs of __call__.

precision: Any = None

numerical precision of the computation, see jax.lax.Precision for details.

use_bias: bool = True

True).

Type:

whether to add a bias to the output (default

layers: int

number of layers.

features: Union[tuple[int, ...], int]

output feature density in each layer. If a single number is given, all layers except the last one will have the same number of features.

kernel_size: int

length of the convolutional kernel.

kernel_init: Callable[[Any, Sequence[int], Any], Union[ndarray, Array]]

initializer for the weights.

bias_init: Callable[[Any, Sequence[int], Any], Union[ndarray, Array]]

initializer for the biases.

hilbert: HomogeneousHilbert

the Hilbert space. Only homogeneous unconstrained Hilbert spaces are supported.

Methods

__call__(inputs)

Computes the log wave-functions for input configurations.

Parameters:

inputs (Union[ndarray, Array]) – configurations with dimensions (batch, Hilbert.size).

Return type:

Union[ndarray, Array]

Returns:

The log psi with dimension (batch,).

activation()

selu applied separately to the real andimaginary parts of it’s input.

The docstring to the original function follows.

Scaled exponential linear unit activation.

Computes the element-wise function:

\[\begin{split}\mathrm{selu}(x) = \lambda \begin{cases} x, & x > 0\\ \alpha e^x - \alpha, & x \le 0 \end{cases}\end{split}\]

where \(\lambda = 1.0507009873554804934193349852946\) and \(\alpha = 1.6732632423543772848170429916717\).

For more information, see Self-Normalizing Neural Networks.

Args:

x : input array

Returns:

An array.

See also:

elu()

Return type:

Array