CFNCell

CFNCell(input_size => hidden_size;
    init_kernel = glorot_uniform,
    init_recurrent_kernel = glorot_uniform,
    bias = true)

Chaos free network unit ^{[Laurent2017]}. See CFN 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.

Equations

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

Forward

cfncell(inp, state)
cfncell(inp)

Arguments

• inp: The input to the cfncell. 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 CFNCell. 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.