Function stacks are layers of functions that are executed simultaneously in one forward, backward, or update pass. Function stacks are created when you either create a test or load a model from disk. Here are some examples of function stacks.

They can be small and simple:

FunctionStack nn = new FunctionStack(
                 new Linear(2, 2, name: "l1 Linear"),
                 new Sigmoid(name: "l1 Sigmoid"),
                 new Linear(2, 2, name: "l2 Linear"));

They can be a little bit bigger:

FunctionStack nn = new FunctionStack(
                 new Convolution2D(1, 2, 3, name: "conv1", gpuEnable: true),// Do not forget the GPU flag if necessary
                 new ReLU(),
                 new MaxPooling(2, 2),
                 new Convolution2D(2, 2, 2, name: "conv2", gpuEnable: true),
                 new ReLU(),
                 new MaxPooling(2, 2),
                 new Linear(8, 2, name: "fl3"),
                 new ReLU(),
                 new Linear(2, 2, name: "fl4")
             );

Or, they can be very large:

FunctionStack nn = new FunctionStack(
                 new Linear(neuronCount * neuronCount, N, name: "l1 Linear"), // L1
                 new BatchNormalization(N, name: "l1 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l1 LeakyReLU"),
                 new Linear(N, N, name: "l2 Linear"), // L2
                 new BatchNormalization(N, name: "l2 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l2 LeakyReLU"),
                 new Linear(N, N, name: "l3 Linear"), // L3
                 new BatchNormalization(N, name: "l3 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l3 LeakyReLU"),
                 new Linear(N, N, name: "l4 Linear"), // L4
                 new BatchNormalization(N, name: "l4 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l4 LeakyReLU"),
                 new Linear(N, N, name: "l5 Linear"), // L5
                 new BatchNormalization(N, name: "l5 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l5 LeakyReLU"),
                 new Linear(N, N, name: "l6 Linear"), // L6
                 new BatchNormalization(N, name: "l6 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l6 LeakyReLU"),
                 new Linear(N, N, name: "l7 Linear"), // L7
                 new BatchNormalization(N, name: "l7 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l7 ReLU"),
                 new Linear(N, N, name: "l8 Linear"), // L8
                 new BatchNormalization(N, name: "l8 BatchNorm"),
                 new LeakyReLU(slope: 0.000001, name: "l8 LeakyReLU"),
                 new Linear(N, N, name: "l9 Linear"), // L9
                 new BatchNormalization(N, name: "l9 BatchNorm"),
                 new PolynomialApproximantSteep(slope: 0.000001, name: "l9 PolynomialApproximantSteep"),
                 new Linear(N, N, name: "l10 Linear"), // L10
                 new BatchNormalization(N, name: "l10 BatchNorm"),
                 new PolynomialApproximantSteep(slope: 0.000001, name: "l10 PolynomialApproximantSteep"),
                 new Linear(N, N, name: "l11 Linear"), // L11
                 new BatchNormalization(N, name: "l11 BatchNorm"),
                 new PolynomialApproximantSteep(slope: 0.000001, name: "l11 PolynomialApproximantSteep"),
                 new Linear(N, N, name: "l12 Linear"), // L12
                 new BatchNormalization(N, name: "l12 BatchNorm"),
                 new PolynomialApproximantSteep(slope: 0.000001, name: "l12 PolynomialApproximantSteep"),
                 new Linear(N, N, name: "l13 Linear"), // L13
                 new BatchNormalization(N, name: "l13 BatchNorm"),
                 new PolynomialApproximantSteep(slope: 0.000001, name: "l13 PolynomialApproximantSteep"),
                 new Linear(N, N, name: "l14 Linear"), // L14
                 new BatchNormalization(N, name: "l14 BatchNorm"),
                 new PolynomialApproximantSteep(slope: 0.000001, name: "l14 PolynomialApproximantSteep"),
                 new Linear(N, 10, name: "l15 Linear") // L15
             );