An implementation of deep neural network with rectifier linear units trained with stochastic gradient descent method and batch normalization. A combination of these methods have achieved state-of-the-art performance in ImageNet classification by overcoming the gradient saturation problem experienced by many deep architecture neural network models in the past. In addition, batch normalization and dropout are implemented as a means of regularization. The deeplearning package is inspired by the darch package and uses its class DArch.

Author | Zhi Ruan [aut, cre], Martin Drees [cph] |

Date of publication | 2016-04-11 18:09:06 |

Maintainer | Zhi Ruan <ryan.zhiruan@gmail.com> |

License | GPL (>= 2) |

Version | 0.1.0 |

https://github.com/rz1988/deeplearning |

**applyDropoutMask:** Applies the given dropout mask to the given data row-wise.

**AR:** Calculates the Accuracy Ratio of a classifier

**AR.DArch:** Calculates the Accruacy Ratio of a given set of probability

**AR.default:** Calculates the Accruacy Ratio of a given set of probability

**AR.numeric:** Calculates the Accruacy Ratio of a given set of probability

**backpropagate_delta_bn:** Calculates the delta functions using backpropagation

**batch_normalization:** Batch Normalization Function that normalizes the input before...

**batch_normalization_differential:** Function that calcualtes the differentials in the batch...

**calcualte_population_mu_sigma:** Calculates the mu and sigmas of a darch instance

**classification_error:** Calculates the classification error

**convert_categorical:** Data proprosess function that covnerts a categorical input to...

**crossEntropyErr:** Calculates the cross entropy error

**finetune_SGD_bn:** Updates a deep neural network's parameters using stochastic...

**generateDropoutMask:** Generates the dropout mask for the deep neural network

**generateDropoutMasksForDarch:** Generates dropout masks for dnn

**matMult:** Calculates the outer product of two matricies

**meanSquareErr:** Calculates the mean squared error

**new_dnn:** Creats a new instance of darch class

**print_weight:** Prints out the weight of a deep neural network

**rectified_linear_unit_function:** Rectified Linear Unit Function

**reset_population_mu_sigma:** Resets the mu and sigmas of a darch instance to 0 and 1

**rsq:** Calculate the RSQ of a regression model Utilitiy function...

**rsq.DArch:** Utilitiy function that calcualtes RSQ of a DArch instance

**rsq.lm:** Utilitiy function that calcualtes RSQ of a linear model

**run_dnn:** Execution function that runs in the batch normalization mode

**train_dnn:** Train a deep neural network

**verticalize:** Creates a matrix by repeating a row vector N times

applyDropoutMask | Man page |

AR | Man page |

AR.DArch | Man page |

AR.default | Man page |

AR.numeric | Man page |

backpropagate_delta_bn | Man page |

batch_normalization | Man page |

batch_normalization_differential | Man page |

calcualte_population_mu_sigma | Man page |

classification_error | Man page |

convert_categorical | Man page |

crossEntropyErr | Man page |

finetune_SGD_bn | Man page |

generateDropoutMask | Man page |

generateDropoutMasksForDarch | Man page |

matMult | Man page |

meanSquareErr | Man page |

new_dnn | Man page |

print_weight | Man page |

rectified_linear_unit_function | Man page |

reset_population_mu_sigma | Man page |

rsq | Man page |

rsq.DArch | Man page |

rsq.lm | Man page |

run_dnn | Man page |

train_dnn | Man page |

verticalize | Man page |

deeplearning

deeplearning/inst

deeplearning/inst/test_batch_normalization_differential.R

deeplearning/inst/test_new_dnn.R

deeplearning/inst/test_ReLU.R

deeplearning/inst/test_finetune_SGD_bn.R

deeplearning/inst/test_train_dnn.R

deeplearning/inst/test_fineTuneFunctions.R

deeplearning/inst/test_run_dnn.R

deeplearning/inst/examples_regression.R

deeplearning/inst/examples_classification.R

deeplearning/NAMESPACE

deeplearning/R

deeplearning/R/new_dnn.R
deeplearning/R/AR.R
deeplearning/R/error_functions.R
deeplearning/R/finetune_SGD.R
deeplearning/R/calculate_mu_sigma.R
deeplearning/R/run_dnn.R
deeplearning/R/dropout.R
deeplearning/R/backpropagate_delta.R
deeplearning/R/train_dnn.R
deeplearning/R/batch_normalization.R
deeplearning/R/rsq.R
deeplearning/R/rectified_linear_unit_function.R
deeplearning/R/util.R
deeplearning/README.md

deeplearning/MD5

deeplearning/DESCRIPTION

deeplearning/man

deeplearning/man/convert_categorical.Rd
deeplearning/man/AR.numeric.Rd
deeplearning/man/AR.DArch.Rd
deeplearning/man/rsq.Rd
deeplearning/man/AR.Rd
deeplearning/man/matMult.Rd
deeplearning/man/generateDropoutMask.Rd
deeplearning/man/train_dnn.Rd
deeplearning/man/classification_error.Rd
deeplearning/man/rsq.lm.Rd
deeplearning/man/batch_normalization_differential.Rd
deeplearning/man/new_dnn.Rd
deeplearning/man/verticalize.Rd
deeplearning/man/calcualte_population_mu_sigma.Rd
deeplearning/man/finetune_SGD_bn.Rd
deeplearning/man/rectified_linear_unit_function.Rd
deeplearning/man/reset_population_mu_sigma.Rd
deeplearning/man/meanSquareErr.Rd
deeplearning/man/rsq.DArch.Rd
deeplearning/man/backpropagate_delta_bn.Rd
deeplearning/man/run_dnn.Rd
deeplearning/man/batch_normalization.Rd
deeplearning/man/applyDropoutMask.Rd
deeplearning/man/generateDropoutMasksForDarch.Rd
deeplearning/man/print_weight.Rd
deeplearning/man/AR.default.Rd
deeplearning/man/crossEntropyErr.Rd
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.