* Lightweight backpropagation neural network.
* This a lightweight library implementating a neural network for use
* in C and C++ programs. It is intended for use in applications that
* just happen to need a simply neural network and do not want to use
* needlessly complex neural network libraries. It features multilayer
* feedforward perceptron neural networks, sigmoidal activation function
* with bias, backpropagation training with settable learning rate and
* momentum, and backpropagation training in batches.
neural network utility is a Neural Networks library for the
C++ Programmer. It is entirely object oriented and focuses
on reducing tedious and confusing problems of programming neural networks.
By this I mean that network layers are easily defined. An
entire multi-layer network can be created in a few lines, and
trained with two functions. Layers can be connected to one another
easily and painlessly.
k-step ahead predictions determined by simulation of the
％ one-step ahead neural network predictor. For NNARMAX
％ models the residuals are set to zero when calculating the
％ predictions. The predictions are compared to the observed output.
％
％ Train a two layer neural network with the Levenberg-Marquardt
％ method.
％
％ If desired, it is possible to use regularization by
％ weight decay. Also pruned (ie. not fully connected) networks can
％ be trained.
％
％ Given a set of corresponding input-output pairs and an initial
％ network,
％ [W1,W2,critvec,iteration,lambda]=marq(NetDef,W1,W2,PHI,Y,trparms)
％ trains the network with the Levenberg-Marquardt method.
％
％ The activation functions can be either linear or tanh. The
％ network architecture is defined by the matrix NetDef which
％ has two rows. The first row specifies the hidden layer and the
％ second row specifies the output layer.
This function applies the Optimal Brain Surgeon (OBS) strategy for
％ pruning neural network models of dynamic systems. That is networks
％ trained by NNARX, NNOE, NNARMAX1, NNARMAX2, or their recursive
％ counterparts.
Train a two layer neural network with a recursive prediction error
％ algorithm ("recursive Gauss-Newton"). Also pruned (i.e., not fully
％ connected) networks can be trained.
％
％ The activation functions can either be linear or tanh. The network
％ architecture is defined by the matrix NetDef , which has of two
％ rows. The first row specifies the hidden layer while the second
％ specifies the output layer.
