FCNN4R: Fast Compressed Neural Networks for R

Provides an interface to kernel routines from the FCNN C++ library. FCNN is based on a completely new Artificial Neural Network representation that offers unmatched efficiency, modularity, and extensibility. FCNN4R provides standard teaching (backpropagation, Rprop, simulated annealing, stochastic gradient) and pruning algorithms (minimum magnitude, Optimal Brain Surgeon), but it is first and foremost an efficient computational engine. Users can easily implement their algorithms by taking advantage of fast gradient computing routines, as well as network reconstruction functionality (removing weights and redundant neurons, reordering inputs, merging networks). Networks can be exported to C functions in order to integrate them into virtually any software solution.

AuthorGrzegorz Klima <gklima@users.sourceforge.net>
Date of publication2016-03-09 00:57:57
MaintainerGrzegorz Klima <gklima@users.sourceforge.net>
LicenseGPL (>= 2)
Version0.6.2

View on CRAN

Man pages

FCNN4R-package: Fast Compressed Neural Networks for R

is.mlp_net: Is it an object of 'mlp_net' class?

mlp_actvfunc2str: Return character string representing activation function

mlp_check_inout: Check validity of inputs and outputs

mlp_check_w: Check validity of weight index

mlp_eval: Evaluation

mlp_export_C: Export multilayer perceptron network to a C function

mlp_net: Create objects of 'mlp_net' class

mlp_net-absolute-weight-indices: Retrieving absolute weight index

mlp_net-accessing-individual-weights: Setting and retrieving status (on/off) and value of...

mlp_net-class: An S4 class representing Multilayer Perception Network.

mlp_net-combining-two-networks: Combining two networks into one

mlp_net-display: Displaying networks (objects of 'mlp_net' class)

mlp_net-export-import: Export and import multilayer perceptron network to/from a...

mlp_net-general-information: General information about network

mlp_net-manipulating-network-inputs: Manipulating network inputs

mlp_net-MSE-gradients: Computing mean squared error, its gradient, and output...

mlp_net-names: Get and set network names

mlp_net-weights-access: Set and retrieve (active) weights' values

mlp_plot: Plotting multilayer perceptron network

mlp_prune_mag: Minimum magnitude pruning

mlp_prune_obs: Optimal Brain Surgeon pruning

mlp_rm_neurons: Remove redundant neurons in a multilayer perceptron network

mlp_rnd_weights: This function sets network weights to random values drawn...

mlp_set_activation: Set network activation functions

mlp_teach_bp: Backpropagation (batch) teaching

mlp_teach_grprop: Rprop teaching - minimising arbitrary objective function

mlp_teach_rprop: Rprop teaching

mlp_teach_sa: Teaching networks using Simulated Annealing

mlp_teach_sgd: Stochastic gradient descent with (optional) RMS weights...

read-write-fcnndataset: Reading and writing datasets in the FCNN format

Files in this package

FCNN4R
FCNN4R/inst
FCNN4R/inst/CITATION
FCNN4R/src
FCNN4R/src/Makevars
FCNN4R/src/fcnn
FCNN4R/src/fcnn/level1.h
FCNN4R/src/fcnn/level2.h
FCNN4R/src/fcnn/fcnncfg.h
FCNN4R/src/fcnn/report.h
FCNN4R/src/fcnn/fcnncfg.R.h
FCNN4R/src/fcnn/level2.cpp
FCNN4R/src/fcnn/error.h
FCNN4R/src/fcnn/level1_impl.h
FCNN4R/src/fcnn/level3.h
FCNN4R/src/fcnn/struct.h
FCNN4R/src/fcnn/report.cpp
FCNN4R/src/fcnn/utils.h
FCNN4R/src/fcnn/utils.cpp
FCNN4R/src/fcnn/level3.cpp
FCNN4R/src/fcnn/activation.h
FCNN4R/src/fcnn/export.cpp
FCNN4R/src/fcnn/export.h
FCNN4R/src/fcnn/struct.cpp
FCNN4R/src/dataset.cpp
FCNN4R/src/Makevars.win
FCNN4R/src/interface.cpp
FCNN4R/NAMESPACE
FCNN4R/R
FCNN4R/R/mlp_prune.R FCNN4R/R/fcnn4r.R FCNN4R/R/mlp_net.R FCNN4R/R/mlp_gteach.R FCNN4R/R/mlp_teach.R FCNN4R/R/mlp_plot.R FCNN4R/R/dataset.R
FCNN4R/MD5
FCNN4R/DESCRIPTION
FCNN4R/man
FCNN4R/man/mlp_check_w.Rd FCNN4R/man/mlp_teach_rprop.Rd FCNN4R/man/mlp_net-combining-two-networks.Rd FCNN4R/man/mlp_net-absolute-weight-indices.Rd FCNN4R/man/mlp_net-manipulating-network-inputs.Rd FCNN4R/man/mlp_net-MSE-gradients.Rd FCNN4R/man/mlp_net-class.Rd FCNN4R/man/read-write-fcnndataset.Rd FCNN4R/man/mlp_teach_sa.Rd FCNN4R/man/mlp_net-export-import.Rd FCNN4R/man/mlp_set_activation.Rd FCNN4R/man/mlp_rnd_weights.Rd FCNN4R/man/mlp_actvfunc2str.Rd FCNN4R/man/mlp_rm_neurons.Rd FCNN4R/man/mlp_net-weights-access.Rd FCNN4R/man/mlp_teach_bp.Rd FCNN4R/man/mlp_export_C.Rd FCNN4R/man/mlp_net-display.Rd FCNN4R/man/mlp_plot.Rd FCNN4R/man/mlp_prune_obs.Rd FCNN4R/man/mlp_net-general-information.Rd FCNN4R/man/mlp_net.Rd FCNN4R/man/mlp_prune_mag.Rd FCNN4R/man/mlp_net-names.Rd FCNN4R/man/mlp_teach_sgd.Rd FCNN4R/man/mlp_net-accessing-individual-weights.Rd FCNN4R/man/mlp_check_inout.Rd FCNN4R/man/FCNN4R-package.Rd FCNN4R/man/mlp_eval.Rd FCNN4R/man/mlp_teach_grprop.Rd FCNN4R/man/is.mlp_net.Rd

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

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