update
abstract fun update(step: Int, epoch: Int, layer: Layer, weightGradients: Tensor, biasGradients: Tensor)
Updates the parameters of the model based on the outputs computed during the forward pass.
Parameters
step
The current step within an epoch.
epoch
The current epoch.
layer
The layer whose parameters are being updated.
weight
The gradients of the weights computed during the backward pass.
bias
The gradients of the biases computed during the backward pass.