chainer.functions.squared_error

chainer.functions.squared_error(x0, x1)[source]

Squared error function.

This function computes the squared error between two variables:

\[(x_0 - x_1)^2\]

where operation is done in elementwise manner. Note that the error is not scaled by 1/2:

Parameters
Returns

A variable holding an array representing the squared error of two inputs.

Return type

Variable

Note

squared_error() and squared_difference() are identical functions, aside from the different argument names. They are both kept for backward compatibility.

Example

>>> x1 = np.arange(6).astype(np.float32)
>>> x1
array([0., 1., 2., 3., 4., 5.], dtype=float32)
>>> x2 = np.array([5, 4, 3, 2, 1, 0]).astype(np.float32)
>>> x2
array([5., 4., 3., 2., 1., 0.], dtype=float32)
>>> y = F.squared_error(x1, x2)
>>> y.shape
(6,)
>>> y.array
array([25.,  9.,  1.,  1.,  9., 25.], dtype=float32)