SinglePassOptimizer

An optimizer that only performs a single pass over training data before updating model parameters.

Inheritors

Functions

Link copied to clipboard
abstract fun batch(cases: List<Exercise>): List<List<Exercise>>

Creates training batches out of the given cases.

Link copied to clipboard
abstract fun update(epoch: Int, layer: Layer, weightGradients: Tensor, biasGradients: Tensor)

Updates the parameters of the model based on the outputs computed during the forward pass.