public protocol RNNCell: Layer where Input == RNNCellInput<TimeStepInput, State>,
                                     Output == RNNCellOutput<TimeStepOutput, State>

A recurrent neural network cell.

  • call(input:state:)

    Extension method

    Returns the new state obtained from applying the RNN cell to the input at the current time step and the previous state.

    Declaration

    func call(input: TimeStepInput, state: State) -> RNNCellOutput<TimeStepOutput, State>

    Parameters

    timeStepInput

    The input at the current time step.

    previousState

    The previous state of the RNN cell.

    Return Value

    The output.