fitted(to:validateOn:eventHandler:)
Fits a fully connected network classifier model to a sequence of examples.
Declaration
func fitted<Input, Validation>(to input: Input, validateOn validation: Validation, eventHandler: EventHandler? = nil) async throws -> FullyConnectedNetworkClassifierModel<Scalar, Label> where Input : Sequence, Validation : Sequence, Input.Element == AnnotatedFeature<MLShapedArray<Scalar>, Label>, Validation.Element == AnnotatedFeature<MLShapedArray<Scalar>, Label>Parameters
- input:
A sequence of examples used for fitting the classifier.
- validation:
A sequence of examples used for validating the fitted classifier.
- eventHandler:
An event handler.
Return Value
The fitted fully connected network classifier model.
Discussion
The training process partitions the input into random batches according to the batch size configuration parameter. Training stops when the validation loss stops improving or when the maximum number of iterations is reached.