Uses of Class
de.jungblut.classification.nn.MultilayerPerceptronCostFunction.NetworkConfiguration
-
Packages that use MultilayerPerceptronCostFunction.NetworkConfiguration Package Description de.jungblut.classification.nn -
-
Uses of MultilayerPerceptronCostFunction.NetworkConfiguration in de.jungblut.classification.nn
Methods in de.jungblut.classification.nn with parameters of type MultilayerPerceptronCostFunction.NetworkConfiguration Modifier and Type Method Description static de.jungblut.math.DoubleMatrix[]MultilayerPerceptronCostFunction. backwardPropagate(de.jungblut.math.DoubleMatrix y, de.jungblut.math.DoubleMatrix[] thetas, de.jungblut.math.DoubleMatrix[] ax, de.jungblut.math.DoubleMatrix[] zx, MultilayerPerceptronCostFunction.NetworkConfiguration conf)static voidMultilayerPerceptronCostFunction. calculateGradients(de.jungblut.math.DoubleMatrix[] thetas, de.jungblut.math.DoubleMatrix[] thetaGradients, de.jungblut.math.DoubleMatrix[] ax, de.jungblut.math.DoubleMatrix[] deltaX, int m, MultilayerPerceptronCostFunction.NetworkConfiguration conf)static doubleMultilayerPerceptronCostFunction. calculateRegularization(de.jungblut.math.DoubleMatrix[] thetas, int m, MultilayerPerceptronCostFunction.NetworkConfiguration conf)static CostGradientTupleMultilayerPerceptronCostFunction. computeNextStep(de.jungblut.math.DoubleVector input, de.jungblut.math.DoubleMatrix x, de.jungblut.math.DoubleMatrix y, MultilayerPerceptronCostFunction.NetworkConfiguration conf)Do a full forward pass and backpropagate the error.static voidMultilayerPerceptronCostFunction. dropoutVisibleLayer(de.jungblut.math.DoubleMatrix x, de.jungblut.math.DoubleMatrix[] ax, MultilayerPerceptronCostFunction.NetworkConfiguration conf)static voidMultilayerPerceptronCostFunction. forwardPropagate(de.jungblut.math.DoubleMatrix[] thetas, de.jungblut.math.DoubleMatrix[] ax, de.jungblut.math.DoubleMatrix[] zx, MultilayerPerceptronCostFunction.NetworkConfiguration conf)
-