A  
abstol [Ann_config] 
Absolute tolerance for the stop criterion.

anniml_predict [Annet]  anniml_predict fnet fwts finputs fpredict makes predictions on a file
of input vectors finputs .

anniml_run [Annet]  anniml_run fnet fwts input runs the network with topology file fnet
and weights file fwts on an input vector input and returns an
output vector y .

anniml_test [Annet]  anniml_test fnet fwts fpatterns tests the network with topology
file fnet and weights file fwts , on patterns fpatterns .

anniml_training [Annet]  anniml_training fnet fwts fpatterns returns a couple (i,w)
where i is the iteration at which the training stopped, and
w is the resulting weights vector.

B  
backprop [Ann_backprop]  backprop fn nn w t (y,a_out,z,a) computes the gradient of the error
function, using backpropagation of the error through the network.

bias_unit [Ann_topology]  bias_units nn u returns true is u is a bias unit of nn , and
false otherwise.

C  
central_diff [Ann_backprop]  central_diff epsilon fn nn w x t computes the gradient of the
error function using central differences instead of backpropagation.

classification_results [Ann_results]  classification_results fn nn patterns w returns a tuple
(sum_squares,mss,normalized_error,entropy,mce,class_mat,
nb_conn,aic,mean_aic,bic,mean_bic) where sum_squares , mss ,
and normalized_error are respectively the raw, mean, and normalized
sum of squares error, entropy is the cross entropy (see [Bishop96],
section 6.9), mce is the mean cross entropy, class_mat is the
matrix of correct/incorrect classifications, nb_conn is the number of
unadjusted parameters (number of weights), aic is the Akaike information
criterion (AIC), mean_aic is the average value of the AIC over all
patterns, bic is Schwartz's Bayes information criterion (BIC), and
mean_bic is the mean value of the BIC .

columns [Ann_config] 
Columns of the patterns file that will be used to build the input
vectors of the neural network.

cross_entropy [Ann_func] 
Crossentropy error function (see [Bishop96], section 6.9).

D  
deriv_cross_entropy [Ann_func] 
Derivative of the crossentropy error function.

deriv_logistic [Ann_func] 
Derivative of the logistic function.

deriv_softmax [Ann_func] 
Derivative of the softmax function.

deriv_sum_of_squares [Ann_func] 
Derivative of the sum of squares error function.

deriv_tanh [Ann_func] 
Derivative of the hyperbolic tangent (as a function of
z !).

dest [Ann_topology]  dest nn k returns the destination unit of connection k of network nn .

dir [Ann_config] 
Working directory.

E  
eta [Ann_config] 
Step of the gradient descent.

F  
finputs [Ann_config] 
File containing input vectors only (whereas patterns files contain also
target vectors).

float_args [Ann_config] 
List of float arguments found when parsing the command line.

fnet [Ann_config] 
Network file, containing the network's topology: units per layer,
connections.

forward [Ann_backprop]  forward fn nn w x returns a tuple (y,a_out,z,a) , where y is the
output vector of the network with functions fn , connections nn ,
and weights w , a_out is the weighted sum of the inputs of the units
belonging to the output layer, z is the output of the hidden units,
and a is the weighted sum of the inputs of the hidden units.

fpatterns [Ann_config] 
Patterns file.

fpredict [Ann_config] 
File where the network's ouptuts are saved of the
predict option
is used.

fprint_list [Ann_topology]  fprint_list ch l prints a list l of integer on channel ch

fprint_network [Ann_topology]  fprint_network ch nn prints the full description of
network nn on channel ch .

fprint_parameters [Ann_config]  fprint_parameters ch prints the global variables used as program
parameters on channel ch .

fprint_pattern [Ann_patterns]  fprint_pattern ch (x,t) prints the input vector x and the
target vector t and channel ch .

fprint_short_topology [Ann_topology]  fprint_short_topology ch nn prints a short description of network
nn on channel ch .

fprint_vector [Ann_func]  print_vector ch x prints the vector x on channel ch

freq_verbose [Ann_config] 
Frequency of the verbose output on stdout (default 10).

fully_connected [Ann_topology]  fully_connected raw_layers builds a fully connected feedforward
network.

fwts [Ann_config] 
Weights file.

G  
get_functions [Ann_config]  get_functions () returns the neural network's functions chosen by the
user (command line options).

H  
hidden [Ann_topology]  hidden layers returns option None when layers contains only
one input and one output layer, and Some (u1,u2) , where u1 and u2
are the first and last hidden units respectively, if there are some
hidden layers.

I  
int_args [Ann_config] 
List of integer arguments found when parsing the command line.

L  
layer_of [Ann_topology]  layer_of nn u returns the number of the layer to which unit u belongs,
according to the network's descriptin in nn .

learning [Ann_config]  learning allows to choose how many patterns are used to compute the
gradient of the error, before making a step in the descent direction
(in the weights space).

log_likelihood [Ann_func] 
Loglikelihood error function

logistic [Ann_func] 
Sigmoid exponential function
logistic(x)=1/(1+exp(x))

M  
max_iter [Ann_config] 
Maximum number of iterations.

mode [Ann_config] 
Program's mode, which may be either
Train , Test , Run , or
Predict .

mu [Ann_config]  mu is the momentum parameter of the gradient descent with momentum
method.

N  
nn_predict [Ann_backprop]  forward fn nn w x returns the output vector y of the network with
functions fn , connections nn , and weights w .

norm [Ann_config] 
Boolean flag deciding if the patterns should be normalized before
being taken as inputs.

normalize [Ann_patterns]  normalize patterns normalizes the input vectors by removing the
average value and dividing by the standard deviation.

O  
opti [Ann_config] 
Optimization method used to minimize the error during the training.

outlayer [Ann_topology]  outlayer layers returns the first and last units of the output layer.

P  
parse_arguments [Ann_config]  parse_arguments () parses the arguments and the options of
the command line.

print_class [Ann_config] 
Boolean flag selecting the type of results printed on the standard
output: classification results when true, or regression results otherwise.

print_classification_results [Ann_results]  print_classification_results res prints different kinds of results
(see classification_results ) on the standard output.

print_regression_results [Ann_results]  print_regression_results res prints different kinds of results
(see regression_results ) on the standard output.

print_results [Ann_results]  print_results fn nn patterns w prc_flag prints various indicators
of the performance of a neural network with functions fn , topology
nn , and weights w , when applied to a set of patterns patterns .

R  
rand [Ann_config] 
Root for the random generator (default 0).

random_weights [Ann_random]  random_weights nn returns a vector of randomly chosen weights
for the network described in nn .

raw_layers [Ann_config] 
Number of units in each layer, without counting the bias units
which are added when the fully connected topology is created.

read_inputs [Ann_patterns]  read_inputs dim_x filename columns reads a file of input vectors
of dimension dim_x , from a file filename .

read_network [Ann_topology]  read_network filename reads a neural network's description
(layers, connections, and bias units) from a file, and returns
the network's topology.

read_patterns [Ann_patterns]  read_patterns dim_x dim_y filename columns reads a patterns file
and returns them as an array of couples (x,t) where
x is an input vector of dimension dim_x , and t is a target
vector of dimension dim_y .

read_weights [Ann_weights]  read_weights filename reads weights from file filename .

regression_results [Ann_results]  regression_results fn nn patterns w returns a tuple
(sum_squares,mss,normalized_error,likelihood,mll,nb_conn,aic,mean_aic,
bic,mean_bic) where sum_squares is the usual sum of squares error,
mss is the mean sum of squares, averaged on the number of patterns,
normalized_error is the sum of squares normalized by the variance of
the target vectors (see section 7.5, p.

reltol [Ann_config] 
Relative tolerance for the stop criterion.

S  
save_network [Ann_topology]  save_network nn filename saves the network's topology nn into
file filename

save_weights [Ann_weights]  save_weights w filename saves the vector of weights w in
file filename .

softmax [Ann_func] 
Softmax function (see [Bishop96], section 6.9):
softmax(a_k)= exp(a_k)/sum_j(exp(a_j) .

source [Ann_topology]  source nn k returns the source unit of connection k of network nn .

stats [Ann_patterns]  stats patterns returns the mean value and standard deviation of
the input vectors of patterns

sum_of_squares [Ann_func] 
"Sum of squares" error function.
