Neural Network Toolbox™

Function Reference

Alphabetical List

Analysis Functions	Analyze network properties
Distance Functions	Compute distance between two vectors
Graphical Interface Functions	Open GUIs for building neural networks
Layer Initialization Functions	Initialize layer weights
Learning Functions	Learning algorithms used to adapt networks
Line Search Functions	Line-search algorithms
Net Input Functions	Sum excitations of layer
Network Initialization Function	Initialize network weights
New Networks Functions	Create network architectures
Network Use Functions	High-level functions to manipulate networks
Performance Functions	Measure network performance
Plotting Functions	Plot and analyze networks and network performance
Processing Functions	Preprocess and postprocess data
Simulink® Support Function	Generate Simulink® block for network simulation
Topology Functions	Arrange neurons of layer according to specific topology
Training Functions	Train networks
Transfer Functions	Transform output of network layer
Utility Functions	Internal utility functions
Vector Functions	Internal functions for network computations
Weight and Bias Initialization Functions	Initialize weights and biases
Weight Functions	Convolution, dot product, scalar product, and distances weight functions

Analysis Functions

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

Distance Functions

boxdist	Distance between two position vectors
dist	Euclidean distance weight function
linkdist	Link distance function
mandist	Manhattan distance weight function

Graphical Interface Functions

nctool	Neural network classification tool
nftool	Open Neural Network Fitting Tool
nntool	Open Network/Data Manager
nntraintool	Neural network training tool
nprtool	Neural network pattern recognition tool
view	View a neural network

Layer Initialization Functions

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

Learning Functions

learncon	Conscience bias learning function
learngd	Gradient descent weight/bias learning function
learngdm	Gradient descent with momentum weight/bias learning function
learnh	Hebb weight learning function
learnhd	Hebb with decay weight learning rule
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
learnp	Perceptron weight and bias learning function
learnpn	Normalized perceptron weight and bias learning function
learnsom	Self-organizing map weight learning function
learnsomb	Batch self-organizing map weight learning function
learnwh	Widrow-Hoff weight and bias learning rule

Line Search Functions

srchbac	1-D minimization using backtracking search
srchbre	1-D interval location using Brent's method
srchcha	1-D minimization using Charalambous' method
srchgol	1-D minimization using golden section search
srchhyb	1-D minimization using hybrid bisection/cubic search

Net Input Functions

netprod	Product net input function
netsum	Sum net input function

Network Initialization Function

initlay

Layer-by-layer network initialization function

Network Use Functions

adapt	Allow neural network to change weights and biases on inputs
disp	Neural network's properties
display	Name and properties of neural network's variables
init	Initialize neural network
sim	Simulate neural network
train	Train neural network

New Networks Functions

network	Create custom neural network
newc	Create competitive layer
newcf	Create cascade-forward backpropagation network
newdtdnn	Create distributed time delay neural network
newelm	Create Elman backpropagation network
newff	Create feedforward backpropagation network
newfftd	Create feedforward input-delay backpropagation network
newfit	Create a fitting network
newgrnn	Design generalized regression neural network
newhop	Create Hopfield recurrent network
newlin	Create linear layer
newlind	Design linear layer
newlrn	Create layered-recurrent network
newlvq	Create learning vector quantization network
newnarx	Create feedforward backpropagation network with feedback from output to input
newnarxsp	Create NARX network in series-parallel arrangement
newp	Create perceptron
newpnn	Design probabilistic neural network
newpr	Create a pattern recognition network
newrb	Design radial basis network
newrbe	Design exact radial basis network
newsom	Create self-organizing map
sp2narx	Convert series-parallel NARX network to parallel (feedback) form

Performance Functions

mae	Mean absolute error performance function
mse	Mean squared error performance function
msereg	Mean squared error with regularization performance function
mseregec	Mean squared error with regularization and economization performance function
sse	Sum squared error performance function

Plotting Functions

hintonw	Hinton graph of weight matrix
hintonwb	Hinton graph of weight matrix and bias vector
plotbr	Plot network performance for Bayesian regularization training
plotconfusion	Plot classification confusion matrix
plotep	Plot weight and bias position on error surface
plotes	Plot error surface of single-input neuron
plotfit	Plot function fit
plotpc	Plot classification line on perceptron vector plot
plotperf	Plot network performance
plotperform	Plot network performance
plotpv	Plot perceptron input target vectors
plotregression	Plot linear regression
plotroc	Plot receiver operating characteristic
plotsom	Plot self-organizing map
plotsomhits	Plot self-organizing map sample hits
plotsomnc	Plot self-organizing map neighbor connections
plotsomnd	Plot self-organizing map neighbor distances
plotsompos	Plot self-organizing map weight positions
plotsomtop	Plot self-organizing map topology
plottrainstate	Plot training state values
plotv	Plot vectors as lines from origin
plotvec	Plot vectors with different colors
postreg	Postprocess trained network response with linear regression

Processing Functions

fixunknowns	Process data by marking rows with unknown values
mapminmax	Process matrices by mapping row minimum and maximum values to [-1 1]
mapstd	Process matrices by mapping each row's means to 0 and deviations to 1
processpca	Process columns of matrix with principal component analysis
removeconstantrows	Process matrices by removing rows with constant values
removerows	Process matrices by removing rows with specified indices

Simulink® Support Function

gensim

Generate Simulink® block for neural network simulation

Topology Functions

gridtop	Gridtop layer topology function
hextop	Hexagonal layer topology function
randtop	Random layer topology function

Training Functions

trainb	Batch training with weight and bias learning rules
trainbfg	BFGS quasi-Newton backpropagation
trainbfgc	BFGS quasi-Newton backpropagation for use with NN model reference adaptive controller
trainbr	Bayesian regularization
trainbuwb	Batch unsupervised weight/bias training
trainc	Cyclical order incremental update
traincgb	Powell-Beale conjugate gradient backpropagation
traincgf	Fletcher-Powell conjugate gradient backpropagation
traincgp	Polak-Ribiére conjugate gradient backpropagation
traingd	Gradient descent backpropagation
traingda	Gradient descent with adaptive learning rule backpropagation
traingdm	Gradient descent with momentum backpropagation
traingdx	Gradient descent with momentum and adaptive learning rule backpropagation
trainlm	Levenberg-Marquardt backpropagation
trainoss	One step secant backpropagation
trainr	Random order incremental training with learning functions
trainrp	Resilient backpropagation (Rprop)
trains	Sequential order incremental training with learning functions
trainscg	Scaled conjugate gradient backpropagation

Transfer Functions

compet	Competitive transfer function
hardlim	Hard limit transfer function
hardlims	Symmetric hard limit transfer function
logsig	Log-sigmoid transfer function
netinv	Inverse transfer function
poslin	Positive linear transfer function
purelin	Linear transfer function
radbas	Radial basis transfer function
satlin	Saturating linear transfer function
satlins	Symmetric saturating linear transfer function
softmax	Softmax transfer function
tansig	Hyperbolic tangent sigmoid transfer function
tribas	Triangular basis transfer function

Utility Functions

calcgx	Calculate weight and bias performance gradient as single vector
calcjejj	Calculate Jacobian performance vector
calcjx	Calculate weight and bias performance Jacobian as single matrix
calcpd	Calculate delayed network inputs
calcperf	Calculate network outputs, signals, and performance
getx	All network weight and bias values as single vector
setx	Set all network weight and bias values with single vector

Vector Functions

combvec	Create all combinations of vectors
con2seq	Convert concurrent vectors to sequential vectors
concur	Create concurrent bias vectors
ind2vec	Convert indices to vectors
minmax	Ranges of matrix rows
normc	Normalize columns of matrix
normr	Normalize rows of matrix
pnormc	Pseudonormalize columns of matrix
quant	Discretize values as multiples of quantity
seq2con	Convert sequential vectors to concurrent vectors
vec2ind	Convert vectors to indices

Weight and Bias Initialization Functions

initcon	Conscience bias initialization function
initsompc	Initialize SOM weights with principal components
initzero	Zero weight and bias initialization function
midpoint	Midpoint weight initialization function
randnc	Normalized column weight initialization function
randnr	Normalized row weight initialization function
rands	Symmetric random weight/bias initialization function
revert	Change network weights and biases to previous initialization values

Weight Functions

convwf	Convolution weight function
dist	Euclidean distance weight function
dotprod	Dot product weight function
mandist	Manhattan distance weight function
negdist	Negative distance weight function
normprod	Normalized dot product weight function
scalprod	Scalar product weight function

Provide feedback about this page

Subobject Properties

Transfer Function Graphs

© 1984-2009- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS