RMSprop class

Implements the RMSprop optimizer.

RMSprop (Root Mean Square Propagation) is an adaptive learning rate optimizer. It maintains a moving average of the square of gradients for each parameter. This adapts the learning rate on a per-parameter basis, decreasing it for parameters with large gradients and increasing it for those with small gradients.

It's often a good choice for recurrent neural networks or when dealing with noisy gradients.

Example

var optimizer = RMSprop(model.parameters, learningRate: 0.001);

Inheritance

• Object
• Optimizer
• RMSprop

Constructors

RMSprop(List<Tensor> parameters, {required double learningRate, double beta = 0.99, double epsilon = 1e-8})

Properties

beta → double

final

epsilon → double

final

hashCode → int

The hash code for this object.

no setter, inherited

learningRate → double

The step size for the gradient updates.

final, inherited

parameters → List<Tensor>

The list of model parameters (weights and biases) that this optimizer will update.

final, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

step() → void

Performs a single optimization step according to the RMSprop update rule.

override

toString() → String

A string representation of this object.

inherited

zeroGrad() → void

Resets the gradients of all parameters to zero.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited