Package org.jetbrains.kotlinx.dl.api.core.regularizer

Types

class L1(value: Float) : L2L1

A regularizer that applies a L1 regularization penalty.

class L2(value: Float) : L2L1

A regularizer that applies a L2 regularization penalty.

L2L1

open class L2L1(l1: Float, l2: Float) : Regularizer

A regularizer that applies both L1 and L2 regularization penalties. The L1 regularization penalty is computed as:

Regularizer

abstract class Regularizer

Regularizers allow you to apply penalties on layer parameters or layer activity during optimization. These penalties are summed into the loss function that the network optimizes.

Properties

DEFAULT_PENALTY

const val DEFAULT_PENALTY: Float = 0.00001f

Default penalty.