Content deleted Content added
Johndburger (talk | contribs) →See also: Removed links already present in the article, per WP:SEEALSO. |
add exponential loss |
||
Line 96:
The cross entropy loss is closely related to the [[Kullback-Leibler divergence]] between the empirical distribution and the predicted distribution. This function is not naturally represented as a product of the true label and the predicted value, but is convex and can be minimized using [[stochastic gradient descent]] methods. The cross entropy loss is ubiquitous in modern [[deep learning|deep neural networks]].
== Exponential loss ==
The exponential loss function is defined as
:<math>V(f(\vec{x}),y) = e^{-yf(\vec{x})}</math>
It penalizes incorrect predictions more than Hinge loss and has larger gradient.
== References ==
| |||