אדם

public class Adam<Model: Differentiable>: Optimizer
where
  Model.TangentVector: VectorProtocol & PointwiseMultiplicative
    & ElementaryFunctions & KeyPathIterable,
  Model.TangentVector.VectorSpaceScalar == Float

אדם אופטימיזציה.

מיישמת את אלגוריתם האופטימיזציה של Adam. אדם היא שיטת השתלשלות גרדיאנט סטוכסטית המחשבת שיעורי למידה אדפטיבית אינדיבידואלית עבור פרמטרים שונים מתוך הערכות של רגעים מסדר ראשון ושני של הגרדיאנטים.

התייחסות: "אדם: שיטה לאופטימיזציה סטוכסטית" (Kingma and Ba, 2014).

דוגמאות:

• אמן סוכן למידה פשוט לחיזוק:

...
// Instantiate an agent's policy - approximated by the neural network (`net`) after defining it 
in advance.
var net = Net(observationSize: Int(observationSize), hiddenSize: hiddenSize, actionCount: actionCount)
// Define the Adam optimizer for the network with a learning rate set to 0.01.
let optimizer = Adam(for: net, learningRate: 0.01)
...
// Begin training the agent (over a certain number of episodes).
while true {
...
    // Implementing the gradient descent with the Adam optimizer:
    // Define the gradients (use withLearningPhase to call a closure under a learning phase).
    let gradients = withLearningPhase(.training) {
        TensorFlow.gradient(at: net) { net -> Tensor<Float> in
            // Return a softmax (loss) function
            return loss = softmaxCrossEntropy(logits: net(input), probabilities: target)
        }
    }
    // Update the differentiable variables of the network (`net`) along the gradients with the Adam 
optimizer.
    optimizer.update(&net, along: gradients)
    ...
    }
}

• אימון רשת יריבות יצירתית (GAN):

...
// Instantiate the generator and the discriminator networks after defining them.
var generator = Generator()
var discriminator = Discriminator()
// Define the Adam optimizers for each network with a learning rate set to 2e-4 and beta1 - to 0.5.
let adamOptimizerG = Adam(for: generator, learningRate: 2e-4, beta1: 0.5)
let adamOptimizerD = Adam(for: discriminator, learningRate: 2e-4, beta1: 0.5)
...
Start the training loop over a certain number of epochs (`epochCount`).
for epoch in 1...epochCount {
    // Start the training phase.
    ...
    for batch in trainingShuffled.batched(batchSize) {
        // Implementing the gradient descent with the Adam optimizer:
        // 1) Update the generator.
        ...
        let 𝛁generator = TensorFlow.gradient(at: generator) { generator -> Tensor<Float> in
            ...
            return loss
            }
        // Update the differentiable variables of the generator along the gradients (`𝛁generator`) 
        // with the Adam optimizer.
        adamOptimizerG.update(&generator, along: 𝛁generator)

        // 2) Update the discriminator.
        ...
        let 𝛁discriminator = TensorFlow.gradient(at: discriminator) { discriminator -> Tensor<Float> in
            ...
            return loss
        }
        // Update the differentiable variables of the discriminator along the gradients (`𝛁discriminator`) 
        // with the Adam optimizer.
        adamOptimizerD.update(&discriminator, along: 𝛁discriminator)
        }
}