Content deleted Content added
Adding local short description: "Type of artificial neural network that uses radial basis functions as activation functions", overriding Wikidata description "an artificial neural network that uses radial basis functions as activation functions" (Shortdesc helper) |
No edit summary |
||
Line 148:
In the first step, the center vectors <math>\mathbf c_i</math> 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 learning|unsupervised]].
Another approach takes into account the difference between the input vector and the network output. This is an example of [[supervised learning]] in the initialization phase. <ref name="Franco">{{Cite journal | doi = 10.1109/TLA.2017.7932707 | title = New Strategies for Initialization and Training of Radial Basis Function Neural Networks | year = 2017 | last1 = Franco | first1 = D. G. B. | last2 = Steiner | first2 = M. T. A. | journal = IEEE Latin America Transactions | volume = 15 | pages = 1182-1188}}</ref>
The second step simply fits a linear model with coefficients <math>w_i</math> 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:
| |||