SGUCell

SGUCell(input_size => hidden_size;
    init_kernel = glorot_uniform,
    init_recurrent_kernel = glorot_uniform,
    bias = true, recurrent_bias = true,
    independent_recurrence = false, integration_mode = :addition)

Simple gated unit (Gao and Glowacka, 16–18 Nov 2016). See SGU 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 input to recurrent bias or not. Default is true.
• recurrent_bias: include recurrent to recurrent 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.

Equations

\[\begin{aligned} \mathbf{x}_g(t) &= \mathbf{W}_{xg} \mathbf{x}(t), \\ \mathbf{z}_g(t) &= \tanh\left(\mathbf{W}_{zg} \left(\mathbf{x}_g(t) \circ \mathbf{h}(t-1)\right) + \mathbf{b}_{zg}\right), \\ \mathbf{z}_{out}(t) &= \operatorname{softplus}\left( \mathbf{z}_g(t) \circ \mathbf{h}(t-1)\right), \\ \mathbf{z}_t &= \operatorname{hard sigmoid}\left( \mathbf{W}_{xz} \mathbf{x}(t) + \mathbf{W}_{hz} \mathbf{h}(t-1) + \mathbf{b}_z\right), \\ \mathbf{h}(t) &= \left(1 - \mathbf{z}_t\right) \circ \mathbf{h}(t-1) + \mathbf{z}_t \circ \mathbf{z}_{out}(t). \end{aligned}\]

Forward

sgucell(inp, state)
sgucell(inp)

Arguments

• inp: The input to the sgucell. 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 SGUCell. 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.