This inheritance list is sorted roughly, but not completely, alphabetically:

[detail level 123]

mic::neural_nets::optimization::artificial_landscapes::DifferentiableFunction< eT >	Abstract class representing interface to a differentiable function
mic::neural_nets::optimization::artificial_landscapes::Beale2DFunction< eT >	2D Beale's function
mic::neural_nets::optimization::artificial_landscapes::Rosenbrock2DFunction< eT >	2D Rosenbrock function
mic::neural_nets::optimization::artificial_landscapes::SphereFunction< eT >	A sphere function - square function generalized to n dimensions
mic::neural_nets::optimization::artificial_landscapes::DifferentiableFunction< double >
mic::neural_nets::optimization::artificial_landscapes::Beale2DFunction< double >
mic::neural_nets::optimization::artificial_landscapes::Rosenbrock2DFunction< double >
mic::neural_nets::optimization::artificial_landscapes::SphereFunction< double >
mic::mlnn::Layer< eT >
mic::mlnn::activation_function::ELU< eT >	Class implementing the layer with Exponential Linear Unit (ELU). http://arxiv.org/pdf/1511.07289v5.pdf
mic::mlnn::activation_function::ReLU< eT >
mic::mlnn::activation_function::Sigmoid< eT >
mic::mlnn::convolution::Convolution< eT >	Class representing a convolution layer, with "valid padding" and variable stride
mic::mlnn::convolution::Cropping< eT >	Class implementing cropping operation - crops the size of image (matrix) by a margin of n pixels on every image side/channel
mic::mlnn::convolution::MaxPooling< eT >	Layer performing max pooling
mic::mlnn::convolution::Padding< eT >	Class implementing padding operation - expanding the size of image (matrix) by a margin of n pixels on every image side
mic::mlnn::cost_function::Softmax< eT >	Softmax activation function
mic::mlnn::experimental::ConvHebbian< eT >	Class implementing a convolutional hebbian layer
mic::mlnn::fully_connected::BinaryCorrelator< eT >	Class implementing a linear, fully connected layer
mic::mlnn::fully_connected::HebbianLinear< eT >	Class implementing a linear, fully connected layer
mic::mlnn::fully_connected::Linear< eT >	Class implementing a linear, fully connected layer
mic::mlnn::fully_connected::SparseLinear< eT >	Class implementing a linear, fully connected layer with sparsity regulation
mic::mlnn::regularisation::Dropout< eT >	Droput layer - a layer used for the regularization of neural network by randomly dropping neurons during training
mic::mlnn::Layer< double >
mic::mlnn::convolution::Convolution< double >
mic::mlnn::fully_connected::Linear< double >
mic::mlnn::Layer< float >
mic::mlnn::convolution::Convolution< float >
mic::mlnn::fully_connected::Linear< float >
mic::mlnn::cost_function::Softmax< float >
mic::neural_nets::loss::Loss< dtype >	Abstract class representing a loss function. Defines interfaces
mic::neural_nets::loss::CrossEntropyLoss< dtype >	Class representing a cross-entropy loss function (classification)
mic::neural_nets::loss::LogLikelihoodLoss< dtype >	Class representing a log-likelihood cost (to be used with softmax logistic regression)
mic::neural_nets::loss::SquaredErrorLoss< dtype >	Class representing a squared error loss function (regression). L = 1/2 sum (t - p)^2
mic::neural_nets::loss::Loss< double >
mic::neural_nets::loss::SquaredErrorLoss< double >
mic::neural_nets::loss::Loss< float >
mic::neural_nets::loss::SquaredErrorLoss< float >
mic::mlnn::MultiLayerNeuralNetwork< eT >	Class representing a multi-layer neural network
mic::mlnn::BackpropagationNeuralNetwork< eT >	Class representing a multi-layer neural network based on backpropagation/gradient descent
mic::mlnn::HebbianNeuralNetwork< eT >	Class representing a multi-layer neural network based on hebbian learning
mic::mlnn::MultiLayerNeuralNetwork< double >
mic::mlnn::BackpropagationNeuralNetwork< double >
mic::mlnn::MultiLayerNeuralNetwork< float >
mic::mlnn::BackpropagationNeuralNetwork< float >
OpenGLContinuousLearningApplication
mic::applications::MNISTPatchReconstructionApplication	Class implementing a simple MNIST patch reconstruction with multi-layer neural net
mic::applications::MNISTPatchSoftmaxApplication	Class implementing a simple MNIST patch softmax classification with multi-layer neural net - imported from previously loaded auto-encoder net and adds softmax layer "at the top"
mic::neural_nets::optimization::OptimizationArray< T >	A dynamic array of optimization functions (a hash-table)
mic::neural_nets::optimization::OptimizationArray< double >
mic::neural_nets::optimization::OptimizationArray< eT >
mic::neural_nets::optimization::OptimizationArray< float >
mic::neural_nets::optimization::OptimizationFunction< eT >	Abstract class representing interface to optimization function
mic::neural_nets::learning::BinaryCorrelatorLearningRule< eT >	Updates according to classical Hebbian rule (wij += ni * x * y)
mic::neural_nets::learning::HebbianRule< eT >	Updates according to classical Hebbian rule (wij += ni * x * y)
mic::neural_nets::learning::NormalizedHebbianRule< eT >	Updates according to classical Hebbian rule (wij += ni * x * y) with additional normalization
mic::neural_nets::learning::NormalizedZerosumHebbianRule< eT >	Updates according to a modified Hebbian rule (wij += ni * f(x, y)) with additional normalization and zero summing for optimal edge detection
mic::neural_nets::optimization::AdaDelta< eT >	Update using AdaDelta - adaptive gradient descent with running average E[g^2] and E[d^2]
mic::neural_nets::optimization::AdaGrad< eT >	Update using AdaGrad - adaptive gradient descent
mic::neural_nets::optimization::AdaGradPID< eT >	AdaGradPID - adaptive gradient descent with proportional, integral and derivative coefficients
mic::neural_nets::optimization::Adam< eT >	Adam - adaptive moment estimation
mic::neural_nets::optimization::AdamID< eT >	AdamID - ADAM with integral and derivative coefficients
mic::neural_nets::optimization::GradientDescent< eT >	Update in the direction of gradient descent
mic::neural_nets::optimization::GradPID< eT >	GradPID - adaptive gradient descent with proportional, integral and derivative coefficients
mic::neural_nets::optimization::Momentum< eT >	Update in the direction of gradient descent - with momentum
mic::neural_nets::optimization::RMSProp< eT >	Update using RMSProp - adaptive gradient descent with running average E[g^2]
Test
Beale2DLandscape	Test fixture - artificial landscape - Beale's function 2D
mic::neural_nets::unit_tests::Conv28x28x1Filter2x28x28s1Double	Test Fixture - layer of input size 28x28x1 and with filter bank of 2 filters of size 28x28 with stride 1, double
mic::neural_nets::unit_tests::Conv2x2x2Filter2x1x1s1Double	Test Fixture - layer of input size 2x2x2 and with filter bank of 2 filters of size 1x1 with stride 1, double. Math example taken from my own calculations;)
mic::neural_nets::unit_tests::Conv3x3x2Filter3x2x2s1Float	Test Fixture - layer of input size 3x3x2 and with filter bank of 3 filters of size 2x2 with stride 1, floats. Math example taken from my whiteboard;)
mic::neural_nets::unit_tests::Conv4x4x1Filter1x2x2s2Float	Test Fixture - layer of input size 4x4x1 and with filter bank of 1 filters of size 2x2 with stride 2, floats. Math example taken from my own YET ANOTHER calculations! ech!
mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double	Test Fixture - layer of input size 4x4x1 and with filter bank of 3 filters of size 1x1 with stride 3, double. Math example taken from my own calculations;)
mic::neural_nets::unit_tests::Conv5x5x1Filter1x2x2s3Float	Test Fixture - layer of input size 5x5x1 and with filter bank of 1 filter of size 2x2 with stride 3 (float). Math example taken from: https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/
mic::neural_nets::unit_tests::Conv5x5x1Filter1x3x3s1Float	Test Fixture - layer of input size 5x5x1 and with filter bank of 1 filter of size 3x3 with stride 1 (floats). Math example taken from: https://ujjwalkarn.me/2016/08/11/intuitive-explanation-convnets/
mic::neural_nets::unit_tests::Conv5x6x1Filter1x4x4s1Float	Test Fixture - layer of input size 5x6x1 and with filter bank of 1 filter of size 4x4 with stride 1, floats. Math example taken from: http://soumith.ch/ex/pages/2014/08/07/why-rotate-weights-convolution-gradient/
mic::neural_nets::unit_tests::Conv7x7x3Filter3x3x3s2Float	Test Fixture - layer of input size 7x7x3 and with filter bank of 2 filters of 3x3 with stride 2 (floats). Math example taken from: http://cs231n.github.io/convolutional-networks/
mic::neural_nets::unit_tests::Conv8x8x1Filter2x4x4s4Double	Test Fixture - layer of input size 8x8x1 and with filter bank of 2 filters of size 4x4 with stride 4, double
mic::neural_nets::unit_tests::Linear1x1Float	Test Fixture - layer of size 1x1, floats, sets W[0] = 1.0 and b[0] = 1.0
mic::neural_nets::unit_tests::Linear2x3Double	Test Fixture - layer of size 2x3, doubles, sets all internal and external values
mic::neural_nets::unit_tests::Linear2x3Float	Test Fixture - layer of size 2x3, floats, sets all internal and external values
mic::neural_nets::unit_tests::Linear50x100Double	Test Fixture - layer of size 50x100, doubles, randomly sets all internal and external values required for numerical gradient verification
mic::neural_nets::unit_tests::Linear5x2Float	Test Fixture - layer of size 5x2, floats
mic::neural_nets::unit_tests::Simple2LayerRegressionNN	Test Fixture - simple ff net with 2 layers
mic::neural_nets::unit_tests::Tutorial2LayerNN	Test Fixture - feed-forward net with 2 layers. A "formalized" example from a step-by-step tutorial: https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/
Rosenbrock2DLandscape	Test fixture - artificial landscape - Rosenbrock function 2D
Softmax4x1Float	Test Fixture - 4x1 softmax layer
Sphere1DLandscape	Test fixture - artificial landscape - sphere function 1D (square function)
Sphere20DLandscape	Test fixture - artificial landscape - sphere function 20D (square function)
Vectors3x2Float	Test Fixture - two vectors of size 3x2, floats
Vectors4x1Float	Test Fixture - two vectors of size 4x1, floats
Vectors4x1Float2	Test Fixture - two predictions of size 4x1, floats