ADALINE network
decision boundary <1> <2>
adaption
custom function
function
parameters
adaptive filter
example
noise cancellation example
prediction application
prediction example
training
adaptive linear networks <1> <2>
amplitude detection
applications
adaptive filtering
aerospace
automotive
banking
defense
electronics
entertainment
financial
insurance
manufacturing
medical <1> <2>
oil and gas exploration
robotics
speech
telecommunications
transportation
architecture
bias connection <1> <2>
input connection <1> <2>
input delays
layer connection <1> <2>
layer delays
number of inputs <1> <2>
number of layers <1> <2>
number of outputs <1> <2>
number of targets <1> <2>
output connection <1> <2>
target connection <1> <2>
backpropagation <1> <2>
algorithm
example
backtracking search
batch training <1> <2> <3>
dynamic networks
static networks
Bayesian framework
benchmark <1> <2>
BFGS quasi-Newton algorithm
bias
connection
definition
initialization function
learning
learning function
learning parameters
subobject <1> <2>
value <1> <2>
box distance
Brent's search
cell array
derivatives
errors
initial layer delay states
input P
input vectors
inputs and targets
inputs property
layer targets
layers property
matrix of concurrent vectors
matrix of sequential vectors
sequence of outputs
sequential inputs
tap delayed inputs
weight matrices and bias vectors
Charalambous' search
classification
input vectors
linear
regions
code
mathematical equivalents
perceptron network
writing
competitive layer
competitive neural network
example
competitive transfer function <1> <2> <3>
concurrent inputs <1> <2>
conjugate gradient algorithm
Fletcher-Reeves update
Polak-Ribiere update
Powell-Beale restarts
scaled
continuous stirred tank reactor
control
control design
electromagnet <1> <2>
feedback linearization <1> <2>
model predictive control <1> <2> <3> <4> <5> <6>
model reference control <1> <2> <3> <4> <5> <6>
NARMA-L2 <1> <2> <3> <4> <5> <6>
plant <1> <2> <3>
robot arm
time horizon
training data
CSTR
custom neural network
dead neurons
decision boundary <1> <2>
definition
demonstrations
appelm1
applin3
definition
demohop1
demohop2
demorb4
nnd10lc
nnd11gn
nnd12cg
nnd12m
nnd12mo
nnd12sd1 <1> <2>
nnd12vl
distance <1> <2>
box
custom function
Euclidean
link
Manhattan
tuning phase
dynamic networks <1> <2>
training <1> <2>
early stopping <1> <2>
electromagnet <1> <2>
Elman network
recurrent connection
Euclidean distance
export
networks <1> <2>
training data
feedback linearization <1> <2>
feedforward network
finite impulse response filter <1> <2>
Fletcher-Reeves update
generalization
regularization
generalized regression network
golden section search
gradient descent algorithm <1> <2>
batch
with momentum <1> <2>
graphical user interface <1> <2>
gridtop topology
Hagan, Martin <1> <2>
hard limit transfer function <1> <2> <3>
heuristic techniques
hidden layer
definition
home neuron
Hopfield network
architecture
design equilibrium point
solution trajectories
stable equilibrium point
target equilibrium points
horizon
hybrid bisection-cubic search
import
networks <1> <2>
training data <1> <2>
incremental training
initial step size function
initialization
additional functions
custom function
definition
function
parameters <1> <2>
input
connection
number
range
size
subobject <1> <2> <3>
input vector
outlier
input vectors
classification
dimension reduction
distance
topology
input weights
definition
inputs
concurrent <1> <2>
sequential <1> <2>
installation guide
Jacobian matrix
Kohonen learning rule
lambda parameter
layer
connection
dimensions
distance function
distances
initialization function
net input function
number
positions
size
subobject
topology function
transfer function
layer weights
definition
learning rate
adaptive
maximum stable
optimal
ordering phase
too large
tuning phase
learning rules
custom
Hebb
Hebb with decay
instar
Kohonen
outstar
supervised learning
unsupervised learning
Widrow-Hoff <1> <2> <3> <4> <5> <6>
learning vector quantization
creation
learning rule <1> <2>
LVQ network
subclasses
target classes
union of two subclasses
least mean square error <1> <2>
Levenberg-Marquardt algorithm
reduced memory
line search functions
backtracking search
Brent's search
Charalambous' search
golden section search
hybrid bisection-cubic search
linear networks
design
linear transfer function <1> <2> <3> <4>
linear transfer functions
linearly dependent vectors
link distance
log-sigmoid transfer function <1> <2> <3>
MADALINE
magnet <1> <2>
Manhattan distance
maximum performance increase
maximum step size
mean square error function
least <1> <2>
memory reduction
model predictive control <1> <2> <3> <4> <5> <6>
model reference control <1> <2> <3> <4> <5> <6>
momentum constant
mu parameter
NARMA-L2 <1> <2> <3> <4> <5> <6>
neighborhood
net input function
custom
network
definition
dynamic <1> <2>
static
network function
network layer
competitive
definition
Network/Data Manager window
neural network
adaptive linear <1> <2>
competitive
custom
definition
feedforward
generalized regression
multiple layer <1> <2> <3>
one layer <1> <2> <3> <4> <5>
probabilistic
radial basis
self organizing
self-organizing feature map
Neural Network Design
Instructor's Manual
overheads
neuron
dead (not allocated)
definition
home
Newton's method
NN predictive control <1> <2> <3> <4> <5> <6>
normalization
inputs and targets
mean and standard deviation
notation
abbreviated <1> <2>
layer
transfer function symbols <1> <2>
numerical optimization
one step secant algorithm
ordering phase learning rate
outlier input vector
output
connection
number
size
subobject <1> <2>
output layer
definition
linear
overdetermined systems
overfitting
pass
definition
pattern recognition
perceptron learning rule <1> <2>
normalized
perceptron network
code
creation
limitations
performance function
custom
modified
parameters
plant <1> <2> <3>
plant identification <1> <2> <3> <4>
Polak-Ribiere update
postprocessing
post-training analysis
Powell-Beale restarts
predictive control <1> <2> <3> <4> <5> <6>
preprocessing
principal component analysis
probabilistic neural network
design
quasi-Newton algorithm
BFGS
radial basis
design
efficient network
function
network
network design
radial basis transfer function
recurrent connection
recurrent networks
regularization
automated
resilient backpropagation
robot arm
self-organizing feature map (SOFM) network
neighborhood
one-dimensional example
two-dimensional example
self-organizing networks
sequential inputs <1> <2>
S-function
sigma parameter
simulation
definition
Simulink
generating networks
NNT blockset <1> <2>
spread constant
squashing functions
static networks
batch training
training
subobject
bias <1> <2> <3>
input <1> <2> <3> <4>
layer <1> <2>
output <1> <2> <3>
target <1> <2> <3>
weight <1> <2> <3> <4> <5>
supervised learning
target output
training set
system identification <1> <2> <3> <4> <5> <6>
tan-sigmoid transfer function
tapped delay line <1> <2>
target
connection
number
size
subobject <1> <2>
target output
time horizon
topologies
custom function
gridtop
topologies for SOFM neuron locations
training
batch <1> <2>
competitive networks
custom function
definition <1> <2>
efficient
faster
function
incremental
ordering phase
parameters
post-training analysis
self organizing feature map
styles
tuning phase
training data
training set
training styles
training with noise
transfer functions
competitive <1> <2> <3>
custom
definition
derivatives
hard limit <1> <2>
linear <1> <2> <3>
log-sigmoid <1> <2> <3>
radial basis
saturating linear
soft maximum
tan-sigmoid
triangular basis
transformation matrix
tuning phase learning rate
tuning phase neighborhood distance
underdetermined systems
unsupervised learning
variable learning rate algorithm
vectors
linearly dependent
weight
definition
delays <1> <2>
initialization function <1> <2>
learning <1> <2>
learning function <1> <2>
learning parameters <1> <2>
size <1> <2>
subobject <1> <2> <3>
value <1> <2> <3>
weight function <1> <2>
weight function
custom
weight matrix
definition
Widrow-Hoff learning rule <1> <2> <3> <4> <5> <6>
workspace (command line)