# chainer.functions.decov¶

chainer.functions.decov(h, reduce='half_squared_sum')[source]

Computes the DeCov loss of h

The output is a variable whose value depends on the value of the option reduce. If it is 'no', it holds a matrix whose size is same as the number of columns of y. If it is 'half_squared_sum', it holds the half of the squared Frobenius norm (i.e. squared of the L2 norm of a matrix flattened to a vector) of the matrix.

Parameters: h (Variable or N-dimensional array) – Variable holding a matrix where the first dimension corresponds to the batches. recude (str) – Reduction option. Its value must be either 'half_squared_sum' or 'no'. Otherwise, ValueError is raised. A variable holding a scalar of the DeCov loss. If reduce is 'no', the output variable holds 2-dimensional array matrix of shape (N, N) where N is the number of columns of y. If it is 'half_squared_sum', the output variable holds a scalar value. Variable

Note

See https://arxiv.org/abs/1511.06068 for details.