chainerx.huber_loss¶
-
chainerx.
huber_loss
()¶ Element-wise Huber loss.
The Huber loss is similar to the squared error but is less sensitive to outliers in the data. It is defined as
\[\begin{split}L_{\delta}(a) = \left \{ \begin{array}{cc} \frac{1}{2} a^2 & {\rm if~|a| \leq \delta} \\ \delta (|a| - \frac{1}{2} \delta) & {\rm otherwise,} \end{array} \right.\end{split}\]where \(a = x - t\) is the difference between the input \(x\) and the target \(t\).
See: Huber loss - Wikipedia.
- Parameters
- Returns
A variable object holding an array representing the Huber loss \(L_{\delta}\) of the two inputs.
- Return type
See also