torchrecurrent.GatedAntisymmetricRNNCell

class torchrecurrent.GatedAntisymmetricRNNCell(input_size, hidden_size, bias=True, activation_fn=<built-in method tanh of type object>, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function normal_>, bias_init=<function zeros_>, epsilon=1.0, gamma=0.0, device=None, dtype=None)

A gated Antisymmetric RNN cell.

Implements the gated update from “AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks” <https://arxiv.org/abs/1902.09689>_.

\[\begin{split}\begin{aligned} \mathbf{z}(t) &= \sigma\Bigl( (\mathbf{W}_{hh} - \mathbf{W}_{hh}^\top - \gamma\,\mathbf{I}) \,\mathbf{h}(t-1) + \mathbf{b}_{hh} + \mathbf{W}_{ih}^z\,\mathbf{x}(t) + \mathbf{b}_{ih}^z \Bigr), \\ \mathbf{h}(t) &= \mathbf{h}(t-1) + \epsilon \,\mathbf{z}(t)\,\circ\, \tanh\Bigl( (\mathbf{W}_{hh} - \mathbf{W}_{hh}^\top - \gamma\,\mathbf{I}) \,\mathbf{h}(t-1) + \mathbf{b}_{hh} + \mathbf{W}_{ih}^x\,\mathbf{x}(t) + \mathbf{b}_{ih}^h \Bigr) \end{aligned}\end{split}\]

where \(\epsilon\) controls the integration step size, \(\gamma\) is a stability damping, and \(\circ\) is element-wise product.

Parameters:

• input_size (int) – Number of expected features in the input inp.

• hidden_size (int) – Number of features in the hidden state.

• bias (bool) – If False, no bias terms are used. Default: True.

• activation_fn (Callable) – Activation to apply (default: torch.tanh).

• kernel_init (Callable) – Initializer for input‐to‐hidden weights (default: nn.init.xavier_uniform_).

• recurrent_kernel_init (Callable) – Initializer for hidden‐to‐hidden weights (default: nn.init.normal_).

• bias_init (Callable) – Initializer for input biases (default: nn.init.zeros_).

• epsilon (float) – Step‐size multiplier for state update. Default: 1.0.

• gamma (float) – Damping term for antisymmetric part. Default: 0.0.

• device (torch.device, optional) – Device on which to place parameters.

• dtype (torch.dtype, optional) – Data type of parameters.

Inputs:

• inp (Tensor): Input at current time step, of shape

  (batch, input_size) or (input_size,).

• state (Tensor or Tuple[Tensor], optional): Previous hidden state,

  of shape (batch, hidden_size) or (hidden_size,). Defaults to zeros.

Outputs:

• new_state (Tensor): Updated hidden state, same shape as state.

weight_ih

Input‐to‐hidden weights, shape (2*hidden_size, input_size).

Type:

Tensor

weight_hh

Hidden‐to‐hidden weights, shape (hidden_size, hidden_size).

Type:

Tensor

bias_ih

Input bias, shape (2*hidden_size,).

Type:

Tensor

bias_hh

Hidden bias, shape (hidden_size,).

Type:

Tensor

Note

This cell splits the input projection into a gate and a candidate, then applies an antisymmetric recurrent transformation plus gating to ensure stable, expressive dynamics.

Examples::

>>> cell = GatedAntisymmetricRNNCell(8, 16, epsilon=0.5, gamma=0.1)
>>> x = torch.randn(4, 8)    # batch=4, input_size=8
>>> h0 = torch.zeros(4, 16)  # batch=4, hidden_size=16
>>> h1 = cell(x, h0)         # new hidden state

__init__(input_size, hidden_size, bias=True, activation_fn=<built-in method tanh of type object>, kernel_init=<function xavier_uniform_>, recurrent_kernel_init=<function normal_>, bias_init=<function zeros_>, epsilon=1.0, gamma=0.0, device=None, dtype=None)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• input_size (int)

• hidden_size (int)

• bias (bool)

• activation_fn (Callable)

• kernel_init (Callable)

• recurrent_kernel_init (Callable)

• bias_init (Callable)

• epsilon (float)

• gamma (float)

• device (device | None)

• dtype (dtype | None)

Methods

__init__(input_size, hidden_size[, bias, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(inp[, state])	Run one step of the recurrent cell.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
init_weights()
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
uses_double_state()	Return True if forward returns (h, c), else just h.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

Attributes

T_destination
call_super_init
dump_patches
weight_ih
weight_hh
bias_ih
bias_hh
training