fully_connected(x, weight, bias=None, num_hidden=None, no_bias=True, flatten=True, **kwargs)

Applies a linear transformation: \(Y = XW^T + b\).

If flatten is set to be true, then the shapes are:

  • data: (batch_size, x1, x2, …, xn)

  • weight: (num_hidden, x1 * x2 * … * xn)

  • bias: (num_hidden,)

  • out: (batch_size, num_hidden)

If flatten is set to be false, then the shapes are:

  • data: (x1, x2, …, xn, input_dim)

  • weight: (num_hidden, input_dim)

  • bias: (num_hidden,)

  • out: (x1, x2, …, xn, num_hidden)

The learnable parameters include both weight and bias.

If no_bias is set to be true, then the bias term is ignored.


The sparse support for FullyConnected is limited to forward evaluation with row_sparse weight and bias, where the length of weight.indices and bias.indices must be equal to num_hidden. This could be useful for model inference with row_sparse weights trained with importance sampling or noise contrastive estimation.

To compute linear transformation with ‘csr’ sparse data, is recommended instead of sparse.FullyConnected.

  • data (NDArray) – Input data.

  • weight (NDArray) – Weight matrix.

  • bias (NDArray) – Bias parameter.

  • num_hidden (int, required) – Number of hidden nodes of the output.

  • no_bias (boolean, optional, default=0) – Whether to disable bias parameter.

  • flatten (boolean, optional, default=1) – Whether to collapse all but the first axis of the input data tensor.


out – The output of this function.

Return type

NDArray or list of NDArrays