附MATLAB 神经网络工具箱

附MATLAB 神经网络工具箱
Graphical user interface functions.
nctool - Neural network classification tool.
nftool - Neural network fitting tool.
nprtool - Neural Network pattern recognition tool.
nntool - Neural Network Toolbox graphical user interface.
nntraintool - Neural network training tool.
view - View a neural network.

Analysis functions.
confusion - Classification confusion matrix.
errsurf - Error surface of single input neuron.
maxlinlr - Maximum learning rate for a linear layer.
roc - Receiver operating characteristic.

Distance functions.
boxdist - Box distance function.
dist - Euclidean distance weight function.
mandist - Manhattan distance weight function.
linkdist - Link distance function.

Formatting data.
combvec - Create all combinations of vectors.
con2seq - Convert concurrent vectors to sequential vectors.
concur - Create concurrent bias vectors.
dividevec - Create all combinations of vectors.
ind2vec - Convert indices to vectors.
minmax - Ranges of matrix rows.
nncopy - Copy matrix or cell array.
normc - Normalize columns of a matrix.
normr - Normalize rows of a matrix.
pnormc - Pseudo-normalize columns of a matrix.
quant - Discretize values as multiples of a quantity.
seq2con - Convert sequential vectors to concurrent vectors.
vec2ind - Convert vectors to indices.

Initialize network functions.
initlay - Layer-by-layer network initialization function.

Initialize layer functions.
initnw - Nguyen-Widrow layer initialization function.
initwb - By-weight-and-bias layer initialization function.

Initialize weight and bias functions.
initcon - Conscience bias initialization function.
initzero - Zero weight/bias initialization function.
initsompc - Initialize SOM weights with principle components.
midpoint - Midpoint weight initialization function.
randnc - Normalized column weight initialization function.
randnr - Normalized row weight initialization function.
rands - Symmetric random weight/bias initialization function.

Learning functions.
learncon - Conscience bias learning function.
learngd - Gradient descent weight/bias learning function.
learngdm - Gradient descent w/momentum weight/bias learning function.
learnh - Hebb weight learning function.
learnhd - Hebb with decay weight learning function.
learnis - Instar weight learning function.
learnk - Kohonen weight learning function.
learnlv1 - LVQ1 weight learning function.
learnlv2 - LVQ2 weight learning function.
learnos - Outstar weight learning function.
learnsomb - Batch self-organizing map weight learning function.
learnp - Perceptron weight/bias learning function.
learnpn - Normalized perceptron weight/bias learning function.
learnsom - Self-organizing map weight learning function.
learnwh - Widrow-Hoff weight/bias learning rule.

Line search functions.
srchbac - Backtracking search.
srchbre - Brent's combination golden section/quadratic interpolation.
srchcha - Charalambous' cubic interpolation.
srchgol - Golden section search.
srchhyb - Hybrid bisection/cubic search.

Net input functions.
netprod - Product net input function.
netsum - Sum net input function.

Network creation functions.
network - Create a custom neural network.
newc - Create a competitive layer.
newcf - Create a cascade-forward backpropagation network.
newdtdnn - Create a distributed time delay neural network.
newelm - Create an Elman backpropagation network.
newfit - Createa a fitting network.
newff - Create a feed-forward backpropagation network.
newfftd - Create a feed-forward input-delay backprop network.
newgrnn - Design a generalized regression neural network.
newhop - Create a Hopfield recurrent network.
newlin - Create a linear layer.
newlind - Design a linear layer.
newlvq - Create a learning vector quantization network.
newnarx - Create a feed-forward backpropagation network with feedback
from output to input.
newnarxsp - Create an NARX network in series-parallel arrangement.
newp - Create a perceptron.
newpnn - Design a probabilistic neural network.
newpr - Create a pattern recognition network.
newrb - Design a radial basis network.
newrbe - Design an exact radial basis network.
newsom - Create a self-organizing map.