class netket.experimental.nn.rnn.RNNCell[source]#

Bases: Module

Recurrent neural network cell that updates the hidden memory at each site.

features: int#

output feature density, should be the last dimension.

abstract __call__(inputs, cell_mem, hidden)[source]#

Applies the RNN cell to a batch of input sites at a given index.

  • inputs – input data with dimensions (batch, in_features).

  • cell_mem – cell memory from the previous site with dimensions (batch, features).

  • hidden – hidden memories from the previous neighbors with dimensions (batch, n_neighbors, features).


  • cell_mem

    the updated cell memory with dimensions (batch, self.features).

  • outputs

    the updated hidden memory with dimensions (batch, self.features), also serves as the output data at the current site for the netket.experimental.nn.rnn.RNNLayer layer.