Training
RBF networks are typically trained by a two-step algorithm. In the first step, the center vectors of the RBF functions in the hidden layer are chosen. This step can be performed in several ways; centers can be randomly sampled from some set of examples, or they can be determined using k-means clustering. Note that this step is unsupervised. A third backpropagation step can be performed to fine-tune all of the RBF net's parameters.
The second step simply fits a linear model with coefficients to the hidden layer's outputs with respect to some objective function. A common objective function, at least for regression/function estimation, is the least squares function:
where
- .
We have explicitly included the dependence on the weights. Minimization of the least squares objective function by optimal choice of weights optimizes accuracy of fit.
There are occasions in which multiple objectives, such as smoothness as well as accuracy, must be optimized. In that case it is useful to optimize a regularized objective function such as
where
and
where optimization of S maximizes smoothness and is known as a regularization parameter.
Read more about this topic: Radial Basis Function Network
Famous quotes containing the word training:
“... the time will come when no servant will be hired without a diploma from some training school, and a girl will as much expect to fit herself for house-maid or cook, as for dressmaker or any trade.”
—Lydia Hoyt Farmer (1842–1903)
“They’ll bust you in the lobby. You look like a training poster for the narc squad.”
—John Guare (b. 1938)
“Dancing is a wonderful training for girls, it’s the first way you learn to guess what a man is going to do before he does it.”
—Christopher Morley (1890–1957)