LightRUCell

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

Light recurrent unit (Ye et al., 2024). See LightRU 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

\[\begin{aligned} \tilde{\mathbf{h}}(t) &= \tanh\left( \mathbf{W}_{ih}^{h} \mathbf{x}(t) \right), \\ \mathbf{f}(t) &= \delta\left( \mathbf{W}_{ih}^{f} \mathbf{x}(t) + \mathbf{W}_{hh}^{f} \mathbf{h}(t-1) + \mathbf{b}^{f} \right), \\ \mathbf{h}(t) &= \left( 1 - \mathbf{f}(t) \right) \odot \mathbf{h}(t-1) + \mathbf{f}(t) \odot \tilde{\mathbf{h}}(t) \end{aligned}\]

Forward

lightrucell(inp, state)
lightrucell(inp)

Arguments

• inp: The input to the lightrucell. 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 LightRUCell. 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.