Interface Optimizer

All Known Implementing Classes:
AdaDeltaOptimizer, AdaGradOptimizer, AdamOptimizer, MomentumOptimizer, RmsPropOptimizer, SgdOptimizer
public interface Optimizer
Optimization technique to tune network's weights parameters used by training algorithm.

  • Field Details

  • Method Details

    • calculateDeltaWeight

      float calculateDeltaWeight(float gradient, int... index)
      Smoothing term to prevent division by zero if sqr grad sum becomes zero 1e-8 should be also tried https://d2l.ai/chapter_optimization/adagrad.html 1e-6 The value to use is 1e-6, 1e-8, Keras uses 1e-7 for adam

    • calculateDeltaWeight

      TensorBase calculateDeltaWeight(TensorBase grad)

    • calculateDeltaBias

      float calculateDeltaBias(float gradient, int idx)

    • calculateDeltaBias

      Tensor1D calculateDeltaBias(Tensor1D grad)

    • setLearningRate

      void setLearningRate(float learningRate)

    • create

      static Optimizer create(OptimizerType type, AbstractLayer layer)
      Factory method to create different types of optimizers
      Parameters:
      type -
      layer -
      Returns: