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:
“Unfortunately, life may sometimes seem unfair to middle children, some of whom feel like an afterthought to a brilliant older sibling and unable to captivate the family’s attention like the darling baby. Yet the middle position offers great training for the real world of lowered expectations, negotiation, and compromise. Middle children who often must break the mold set by an older sibling may thereby learn to challenge family values and seek their own identity.”
—Marianne E. Neifert (20th century)
“I’m not suggesting that all men are beautiful, vulnerable boys, but we all started out that way. What happened to us? How did we become monsters of feminist nightmares? The answer, of course, is that we underwent a careful and deliberate process of gender training, sometimes brutal, always dehumanizing, cutting away large chunks of ourselves. Little girls went through something similarly crippling. If the gender training was successful, we each ended up being half a person.”
—Frank Pittman (20th century)
“When a man goes through six years’ training to be a doctor he will never be the same. He knows too much.”
—Enid Bagnold (1889–1981)