GatedAntisymmetricRNNCell

GatedAntisymmetricRNNCell(input_size => hidden_size, [activation];
    init_kernel = glorot_uniform,
    init_recurrent_kernel = glorot_uniform,
    independent_recurrence = false, integration_mode = :addition,
    bias = true, recurrent_bias = true,
    epsilon=1.0, gamma = 0.0)

Antisymmetric recurrent cell with gating (Chang et al., 2019). See GatedAntisymmetricRNN for a layer that processes entire sequences.

Arguments

• input_size => hidden_size: input and inner dimension of the layer.

Keyword arguments

• init_kernel: initializer for the input to hidden weights. Default is glorot_uniform.
• init_recurrent_kernel: initializer for the hidden to hidden weights. Default is glorot_uniform.
• bias: include a bias or not. Default is true.
• independent_recurrence: flag to toggle independent recurrence. If true, the recurrent to recurrent weights are a vector instead of a matrix. Default false.
• integration_mode: determines how the input and hidden projections are combined. The options are :addition and :multiplicative_integration. Defaults to :addition.
• epsilon: step size. Default is 1.0.
• gamma: strength of diffusion. Default is 0.0.

Equations

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

Forward

asymrnncell(inp, state)
asymrnncell(inp)

Arguments

• inp: The input to the asymrnncell. It should be a vector of size input_size or a matrix of size input_size x batch_size.
• state: The hidden state of the GatedAntisymmetricRNNCell. It should be a vector of size hidden_size or a matrix of size hidden_size x batch_size. If not provided, it is assumed to be a vector of zeros, initialized by Flux.initialstates.

Returns

• A tuple (output, state), where both elements are given by the updated state new_state, a tensor of size hidden_size or hidden_size x batch_size.