JANETCell

JANETCell(input_size => hidden_size;
    init_kernel = glorot_uniform,
    init_recurrent_kernel = glorot_uniform,
    bias = true, recurrent_bias = true,
    independent_recurrence = false, integration_mode = :addition,
    beta_value=1.0)

Just another network unit (van der Westhuizen and Lasenby, 2018). See JANET 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.
• beta_value: control over the input data flow. Default is 1.0.

Equations

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

Forward

janetcell(inp, (state, cstate))
janetcell(inp)

Arguments

• inp: The input to the rancell. It should be a vector of size input_size or a matrix of size input_size x batch_size.
• (state, cstate): A tuple containing the hidden and cell states of the RANCell. They should be vectors of size hidden_size or matrices of size hidden_size x batch_size. If not provided, they are assumed to be vectors of zeros, initialized by Flux.initialstates.

Returns

• A tuple (output, state), where output = new_state is the new hidden state and state = (new_state, new_cstate) is the new hidden and cell state. They are tensors of size hidden_size or hidden_size x batch_size.