|
SOMLearningRun Method
|
Runs learning iteration.
Namespace:
Accord.Neuro.Learning
Assembly:
Accord.Neuro (in Accord.Neuro.dll) Version: 3.8.0
Syntax public double Run(
double[] input
)
Public Function Run (
input As Double()
) As Double
Request Example
View SourceParameters
- input
- Type: SystemDouble
Input vector.
Return Value
Type:
DoubleReturns learning error - summary absolute difference between neurons' weights
and appropriate inputs. The difference is measured according to the neurons
distance to the winner neuron.
Implements
IUnsupervisedLearningRun(Double)Remarks The method runs one learning iterations - finds winner neuron (the neuron
which has weights with values closest to the specified input vector) and updates its weight
(as well as weights of neighbor neurons) in the way to decrease difference with the specified
input vector.
See Also