Package deepboof.backward

  • Interface Summary
    Interface Description
    DActivationReLU<T extends deepboof.Tensor<T>>
    Interface of ActivationReLU which adds functionality for the backwards step.
    DActivationSigmoid<T extends deepboof.Tensor<T>>
    Interface of ActivationSigmoid which adds functionality for the backwards step.
    DActivationTanH<T extends deepboof.Tensor<T>>
    Interface of ActivationTanH which adds functionality for the backwards step.
    DBatchNorm<T extends deepboof.Tensor<T>>
    Implementation of batch normalization for training networks.
    DFunctionBatchNorm<T extends deepboof.Tensor<T>>
    Implementation of Batch Normalization for training networks.
    DFunctionDropOut<T extends deepboof.Tensor<T>>
    Drop out is a technique introduced by [1] for regularizing a network and helps prevents over fitting.
    DFunctionLinear<T extends deepboof.Tensor<T>>
    Interface of FunctionLinear which adds functionality for the backwards step.
    DSpatialBatchNorm<T extends deepboof.Tensor<T>>
    Interface of Spatial Batch Normalization for training networks.
    DSpatialConvolve2D<T extends deepboof.Tensor<T>>
    Implementation of Spatial Convolve 2D for training networks.
    DSpatialMaxPooling<T extends deepboof.Tensor<T>>
    Interface of SpatialMaxPooling which adds functionality for the backwards step.
    DSpatialPadding2D<T extends deepboof.Tensor<T>>
    Interface for computing the gradient of a padded spatial tensor.
    DSpatialPadding2D_F64  
    NumericalGradient<T extends deepboof.Tensor<T>>
    Given a Function implementations of this interface will compute the gradient of its inputs and parameters.