# FCNN4R v0.6.2

0

0th

Percentile

## 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.

## Functions in FCNN4R

 Name Description FCNN4R-package Fast Compressed Neural Networks for R mlp_net-absolute-weight-indices Retrieving absolute weight index mlp_actvfunc2str Return character string representing activation function is.mlp_net Is it an object of mlp_net class? mlp_net-accessing-individual-weights Setting and retrieving status (on/off) and value of individual weight(s) mlp_check_w Check validity of weight index mlp_net-class An S4 class representing Multilayer Perception Network. mlp_eval Evaluation mlp_check_inout Check validity of inputs and outputs mlp_export_C Export multilayer perceptron network to a C function mlp_net-weights-access Set and retrieve (active) weights' values mlp_net-manipulating-network-inputs Manipulating network inputs mlp_plot Plotting multilayer perceptron network mlp_net-export-import Export and import multilayer perceptron network to/from a text file in FCNN format mlp_net-general-information General information about network mlp_net Create objects of mlp_net class mlp_net-MSE-gradients Computing mean squared error, its gradient, and output derivatives mlp_net-combining-two-networks Combining two networks into one mlp_net-names Get and set network names mlp_net-display Displaying networks (objects of mlp_net class) mlp_teach_rprop Rprop teaching mlp_teach_bp Backpropagation (batch) teaching mlp_teach_grprop Rprop teaching - minimising arbitrary objective function mlp_prune_mag Minimum magnitude pruning mlp_prune_obs Optimal Brain Surgeon pruning mlp_teach_sa Teaching networks using Simulated Annealing mlp_set_activation Set network activation functions mlp_teach_sgd Stochastic gradient descent with (optional) RMS weights scaling, weight decay, and momentum mlp_rm_neurons Remove redundant neurons in a multilayer perceptron network mlp_rnd_weights This function sets network weights to random values drawn from uniform distribution. read-write-fcnndataset Reading and writing datasets in the FCNN format No Results!