MomentumOptimizer

Constructors

constructor()

open override val epochCount: Int

Lists the measurements taken by this object.

open override fun batch(cases: List<Exercise>): List<List<Exercise>>

Creates training batches out of the given cases.

Collects all measures into a single immutable object

open override fun data(key: Measurement<Float>): DataList<Float, Float>

open override fun onBatchEnd(batch: List<Exercise>)

open override fun onBatchStart(batch: List<Exercise>)

open override fun onCost(cost: Double)

open override fun onEpochEnd(epoch: Int, context: ComputationContext)

open override fun onEpochStart(epoch: Int, context: ComputationContext)

open override fun onGradient()

open override fun onSampleEnd(sample: Exercise)

open override fun onSampleStart(sample: Exercise)

open override 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.