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.
|Author||Grzegorz Klima <email@example.com>|
|Date of publication||2016-03-09 00:57:57|
|Maintainer||Grzegorz Klima <firstname.lastname@example.org>|
|License||GPL (>= 2)|
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_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