Loss Functions
The choice of loss function is a determining factor on the function that will be chosen by the learning algorithm. The loss function also affects the convergence rate for an algorithm. It is important for the loss function to be convex.
Different loss functions are used depending on whether the problem is one of regression or one of classification.
Read more about this topic: Statistical Learning Theory
Famous quotes containing the words loss and/or functions:
“... the loss of belief in future states is politically, though certainly not spiritually, the most significant distinction between our present period and the centuries before. And this loss is definite. For no matter how religious our world may turn again, or how much authentic faith still exists in it, or how deeply our moral values may be rooted in our religious systems, the fear of hell is no longer among the motives which would prevent or stimulate the actions of a majority.”
—Hannah Arendt (1906–1975)
“Mark the babe
Not long accustomed to this breathing world;
One that hath barely learned to shape a smile,
Though yet irrational of soul, to grasp
With tiny finger—to let fall a tear;
And, as the heavy cloud of sleep dissolves,
To stretch his limbs, bemocking, as might seem,
The outward functions of intelligent man.”
—William Wordsworth (1770–1850)