|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<HTML
><HEAD
><TITLE
>Fast Artificial Neural Network Library</TITLE
><link href="../style.css" rel="stylesheet" type="text/css"><META
NAME="GENERATOR"
CONTENT="Modular DocBook HTML Stylesheet Version 1.7"><LINK
REL="NEXT"
TITLE="Introduction"
HREF="c13.html"></HEAD
><BODY
CLASS="book"
BGCOLOR="#FFFFFF"
TEXT="#000000"
LINK="#0000FF"
VLINK="#840084"
ALINK="#0000FF"
><DIV
CLASS="BOOK"
><A
NAME="AEN1"
></A
><DIV
CLASS="TITLEPAGE"
><H1
CLASS="title"
><A
NAME="bookinfo"
>Fast Artificial Neural Network Library</A
></H1
><H3
CLASS="author"
><A
NAME="AEN5"
></A
>Steffen Nissen</H3
><H3
CLASS="author"
><A
NAME="AEN8"
></A
>Evan Nemerson</H3
><P
CLASS="copyright"
>Copyright © 2004 </P
><HR></DIV
><DIV
CLASS="TOC"
><DL
><DT
><B
>Table of Contents</B
></DT
><DT
>1. <A
HREF="c13.html"
>Introduction</A
></DT
><DD
><DL
><DT
>1.1. <A
HREF="c13.html#intro.dl"
>Getting FANN</A
></DT
><DT
>1.2. <A
HREF="x26.html"
>Installation</A
></DT
><DD
><DL
><DT
>1.2.1. <A
HREF="x26.html#intro.install.rpm"
>RPMs</A
></DT
><DT
>1.2.2. <A
HREF="x26.html#intro.install.deb"
>DEBs</A
></DT
><DT
>1.2.3. <A
HREF="x26.html#intro.install.win32"
>Windows</A
></DT
><DT
>1.2.4. <A
HREF="x26.html#intro.install.src"
>Compiling from source</A
></DT
></DL
></DD
><DT
>1.3. <A
HREF="x68.html"
>Getting Started</A
></DT
><DD
><DL
><DT
>1.3.1. <A
HREF="x68.html#intro.start.train"
>Training</A
></DT
><DT
>1.3.2. <A
HREF="x68.html#intro.start.execution"
>Execution</A
></DT
></DL
></DD
><DT
>1.4. <A
HREF="x100.html"
>Getting Help</A
></DT
></DL
></DD
><DT
>2. <A
HREF="c104.html"
>Advanced Usage</A
></DT
><DD
><DL
><DT
>2.1. <A
HREF="c104.html#adv.adj"
>Adjusting Parameters</A
></DT
><DT
>2.2. <A
HREF="x141.html"
>Network Design</A
></DT
><DT
>2.3. <A
HREF="x148.html"
>Understanding the Error Value</A
></DT
><DT
>2.4. <A
HREF="x161.html"
>Training and Testing</A
></DT
><DT
>2.5. <A
HREF="x181.html"
>Avoid Over-Fitting</A
></DT
><DT
>2.6. <A
HREF="x184.html"
>Adjusting Parameters During Training</A
></DT
></DL
></DD
><DT
>3. <A
HREF="c189.html"
>Fixed Point Usage</A
></DT
><DD
><DL
><DT
>3.1. <A
HREF="c189.html#fixed.train"
>Training a Fixed Point ANN</A
></DT
><DT
>3.2. <A
HREF="x203.html"
>Running a Fixed Point ANN</A
></DT
><DT
>3.3. <A
HREF="x217.html"
>Precision of a Fixed Point ANN</A
></DT
></DL
></DD
><DT
>4. <A
HREF="c225.html"
>Neural Network Theory</A
></DT
><DD
><DL
><DT
>4.1. <A
HREF="c225.html#theory.neural_networks"
>Neural Networks</A
></DT
><DT
>4.2. <A
HREF="x241.html"
>Artificial Neural Networks</A
></DT
><DT
>4.3. <A
HREF="x246.html"
>Training an ANN</A
></DT
></DL
></DD
><DT
>5. <A
HREF="c253.html"
>API Reference</A
></DT
><DD
><DL
><DT
>5.1. <A
HREF="c253.html#api.sec.create_destroy"
>Creation, Destruction, and Execution</A
></DT
><DD
><DL
><DT
><A
HREF="r258.html"
>fann_create</A
> -- Create a new artificial neural network, and return a pointer to it.</DT
><DT
><A
HREF="r285.html"
>fann_create_array</A
> -- Create a new artificial neural network, and return a pointer to it.</DT
><DT
><A
HREF="r315.html"
>fann_create_shortcut</A
> -- Create a new artificial neural network with shortcut connections, and return a pointer to it.</DT
><DT
><A
HREF="r339.html"
>fann_create_shortcut_array</A
> -- Create a new artificial neural network with shortcut connections, and return a pointer to it.</DT
><DT
><A
HREF="r361.html"
>fann_destroy</A
> -- Destroy an ANN.</DT
><DT
><A
HREF="r376.html"
>fann_run</A
> -- Run (execute) an ANN.</DT
><DT
><A
HREF="r396.html"
>fann_randomize_weights</A
> -- Give each connection a random weight.</DT
><DT
><A
HREF="r421.html"
>fann_init_weights</A
> -- Initialize the weight of each connection.</DT
><DT
><A
HREF="r448.html"
>fann_print_connections</A
> -- Prints the connections of an ann.</DT
></DL
></DD
><DT
>5.2. <A
HREF="x472.html"
>Input/Output</A
></DT
><DD
><DL
><DT
><A
HREF="r474.html"
>fann_save</A
> -- Save an ANN to a file.</DT
><DT
><A
HREF="r494.html"
>fann_save_to_fixed</A
> -- Save an ANN to a fixed-point file.</DT
><DT
><A
HREF="r519.html"
>fann_create_from_file</A
> -- Load an ANN from a file.</DT
></DL
></DD
><DT
>5.3. <A
HREF="x534.html"
>Training</A
></DT
><DD
><DL
><DT
><A
HREF="r536.html"
>fann_train</A
> -- Train an ANN.</DT
><DT
><A
HREF="r557.html"
>fann_test</A
> -- Tests an ANN.</DT
><DT
><A
HREF="r577.html"
>fann_get_MSE</A
> -- Return the mean square error of an ANN.</DT
><DT
><A
HREF="r593.html"
>fann_reset_MSE</A
> -- Reset the mean square error of an ANN.</DT
></DL
></DD
><DT
>5.4. <A
HREF="x609.html"
>Training Data</A
></DT
><DD
><DL
><DT
><A
HREF="r611.html"
>fann_read_train_from_file</A
> -- Read training data from a file.</DT
><DT
><A
HREF="r629.html"
>fann_save_train</A
> -- Save training data.</DT
><DT
><A
HREF="r648.html"
>fann_save_train_to_fixed</A
> -- Save training data as fixed point.</DT
><DT
><A
HREF="r670.html"
>fann_destroy_train</A
> -- Destroy training data.</DT
><DT
><A
HREF="r685.html"
>fann_train_epoch</A
> -- Trains one epoch.</DT
><DT
><A
HREF="r709.html"
>fann_test_data</A
> -- Calculates the mean square error for a set of data.</DT
><DT
><A
HREF="r726.html"
>fann_train_on_data</A
> -- Train an ANN.</DT
><DT
><A
HREF="r761.html"
>fann_train_on_data_callback</A
> -- Train an ANN.</DT
><DT
><A
HREF="r806.html"
>fann_train_on_file</A
> -- Train an ANN.</DT
><DT
><A
HREF="r841.html"
>fann_train_on_file_callback</A
> -- Train an ANN.</DT
><DT
><A
HREF="r886.html"
>fann_shuffle_train_data</A
> -- Shuffle the training data.</DT
><DT
><A
HREF="r902.html"
>fann_merge_train_data</A
> -- Merge two sets of training data.</DT
><DT
><A
HREF="r922.html"
>fann_duplicate_train_data</A
> -- Copies a set of training data.</DT
></DL
></DD
><DT
>5.5. <A
HREF="x938.html"
>Options</A
></DT
><DD
><DL
><DT
><A
HREF="r940.html"
>fann_print_parameters</A
> -- Prints all of the parameters and options of the ANN.</DT
><DT
><A
HREF="r954.html"
>fann_get_training_algorithm</A
> -- Retrieve training algorithm from a network.</DT
><DT
><A
HREF="r972.html"
>fann_set_training_algorithm</A
> -- Set a network's training algorithm.</DT
><DT
><A
HREF="r993.html"
>fann_get_learning_rate</A
> -- Retrieve learning rate from a network.</DT
><DT
><A
HREF="r1007.html"
>fann_set_learning_rate</A
> -- Set a network's learning rate.</DT
><DT
><A
HREF="r1024.html"
>fann_get_activation_function_hidden</A
> -- Get the activation function used in the hidden layers.</DT
><DT
><A
HREF="r1040.html"
>fann_set_activation_function_hidden</A
> -- Set the activation function for the hidden layers.</DT
><DT
><A
HREF="r1060.html"
>fann_get_activation_function_output</A
> -- Get the activation function of the output layer.</DT
><DT
><A
HREF="r1076.html"
>fann_set_activation_function_output</A
> -- Set the activation function for the output layer.</DT
><DT
><A
HREF="r1096.html"
>fann_get_activation_steepness_hidden</A
> -- Retrieve the steepness of the activation function of the hidden layers.</DT
><DT
><A
HREF="r1112.html"
>fann_set_activation_steepness_hidden</A
> -- Set the steepness of the activation function of the hidden layers.</DT
><DT
><A
HREF="r1133.html"
>fann_get_activation_steepness_output</A
> -- Retrieve the steepness of the activation function of the output layer.</DT
><DT
><A
HREF="r1149.html"
>fann_set_activation_steepness_output</A
> -- Set the steepness of the activation function of the output layer.</DT
><DT
><A
HREF="r1170.html"
>fann_set_train_error_function</A
> -- Sets the training error function to be used.</DT
><DT
><A
HREF="r1191.html"
>fann_get_train_error_function</A
> -- Gets the training error function to be used.</DT
><DT
><A
HREF="r1209.html"
>fann_get_quickprop_decay</A
> -- Get the decay parameter used by the quickprop training.</DT
><DT
><A
HREF="r1224.html"
>fann_set_quickprop_decay</A
> -- Set the decay parameter used by the quickprop training.</DT
><DT
><A
HREF="r1242.html"
>fann_get_quickprop_mu</A
> -- Get the mu factor used by quickprop training.</DT
><DT
><A
HREF="r1257.html"
>fann_set_quickprop_mu</A
> -- Set the mu factor used by quickprop training.</DT
><DT
><A
HREF="r1275.html"
>fann_get_rprop_increase_factor</A
> -- Get the increase factor used by RPROP training.</DT
><DT
><A
HREF="r1290.html"
>fann_set_rprop_increase_factor</A
> -- Get the increase factor used by RPROP training.</DT
><DT
><A
HREF="r1308.html"
>fann_get_rprop_decrease_factor</A
> -- Get the decrease factor used by RPROP training.</DT
><DT
><A
HREF="r1323.html"
>fann_set_rprop_decrease_factor</A
> -- Set the decrease factor used by RPROP training.</DT
><DT
><A
HREF="r1341.html"
>fann_get_rprop_delta_min</A
> -- Get the minimum step-size used by RPROP training.</DT
><DT
><A
HREF="r1356.html"
>fann_set_rprop_delta_min</A
> -- Set the minimum step-size used by RPROP training.</DT
><DT
><A
HREF="r1374.html"
>fann_get_rprop_delta_max</A
> -- Get the maximum step-size used by RPROP training.</DT
><DT
><A
HREF="r1389.html"
>fann_set_rprop_delta_max</A
> -- Set the maximum step-size used by RPROP training.</DT
><DT
><A
HREF="r1407.html"
>fann_get_num_input</A
> -- Get the number of neurons in the input layer.</DT
><DT
><A
HREF="r1422.html"
>fann_get_num_output</A
> -- Get number of neurons in the output layer.</DT
><DT
><A
HREF="r1437.html"
>fann_get_total_neurons</A
> -- Get the total number of neurons in a network.</DT
><DT
><A
HREF="r1452.html"
>fann_get_total_connections</A
> -- Get the total number of connections in a network.</DT
><DT
><A
HREF="r1467.html"
>fann_get_decimal_point</A
> -- Get the position of the decimal point.</DT
><DT
><A
HREF="r1483.html"
>fann_get_multiplier</A
> -- Get the multiplier.</DT
></DL
></DD
><DT
>5.6. <A
HREF="x1499.html"
>Error Handling</A
></DT
><DD
><DL
><DT
><A
HREF="r1501.html"
>fann_get_errno</A
> -- Return the numerical representation of the last error.</DT
><DT
><A
HREF="r1516.html"
>fann_get_errstr</A
> -- Return the last error.</DT
><DT
><A
HREF="r1533.html"
>fann_reset_errno</A
> -- Reset the last error number.</DT
><DT
><A
HREF="r1547.html"
>fann_reset_errstr</A
> -- Reset the last error string.</DT
><DT
><A
HREF="r1561.html"
>fann_set_error_log</A
> -- Set the error log to a file descriptor.</DT
><DT
><A
HREF="r1580.html"
>fann_print_error</A
> -- Print the last error to the error log.</DT
></DL
></DD
><DT
>5.7. <A
HREF="x1595.html"
>Data Structures</A
></DT
><DD
><DL
><DT
><A
HREF="r1597.html"
>struct fann</A
> -- Describes a neural network.</DT
><DT
><A
HREF="r1837.html"
>struct fann_train_data</A
> -- Describes a set of training data.</DT
><DT
><A
HREF="r1900.html"
>struct fann_error</A
> -- Describes an error.</DT
><DT
><A
HREF="r1936.html"
>struct fann_neuron</A
> -- Describes an individual neuron.</DT
><DT
><A
HREF="r1970.html"
>struct fann_layer</A
> -- Describes a layer in a network.</DT
></DL
></DD
><DT
>5.8. <A
HREF="x1994.html"
>Constants</A
></DT
><DD
><DL
><DT
><A
HREF="r1996.html"
>Training algorithms</A
> -- Constants representing training algorithms.</DT
><DT
><A
HREF="r2030.html"
>Activation Functions</A
> -- Constants representing activation functions.</DT
><DT
><A
HREF="r2077.html"
>Training Error Functions</A
> -- Constants representing errors functions.</DT
><DT
><A
HREF="r2099.html"
>Error Codes</A
> -- Constants representing errors.</DT
></DL
></DD
><DT
>5.9. <A
HREF="x2169.html"
>Internal Functions</A
></DT
><DD
><DL
><DT
>5.9.1. <A
HREF="x2169.html#api.sec.create_destroy.internal"
>Creation And Destruction</A
></DT
><DT
>5.9.2. <A
HREF="x2169.html#api.sec.io.internal"
>Input/Output</A
></DT
><DT
>5.9.3. <A
HREF="x2169.html#api.sec.train_data.internal"
>Training Data</A
></DT
><DT
>5.9.4. <A
HREF="x2169.html#api.sec.io.errors"
>Error Handling</A
></DT
><DT
>5.9.5. <A
HREF="x2169.html#api.sec.options.internal"
>Options</A
></DT
></DL
></DD
><DT
>5.10. <A
HREF="x2399.html"
>Deprecated Functions</A
></DT
><DD
><DL
><DT
>5.10.1. <A
HREF="x2399.html#api.sec.error.deprecated"
>Mean Square Error</A
></DT
><DT
>5.10.2. <A
HREF="x2399.html#api.sec.steepness.deprecated"
>Get and set activation function steepness.</A
></DT
></DL
></DD
></DL
></DD
><DT
>6. <A
HREF="c2519.html"
>PHP Extension</A
></DT
><DD
><DL
><DT
>6.1. <A
HREF="c2519.html#php.install"
>Installation</A
></DT
><DD
><DL
><DT
>6.1.1. <A
HREF="c2519.html#php.install.pear"
>Using PEAR</A
></DT
><DT
>6.1.2. <A
HREF="c2519.html#php.install.ext"
>Compiling into PHP</A
></DT
></DL
></DD
><DT
>6.2. <A
HREF="x2553.html"
>API Reference</A
></DT
><DD
><DL
><DT
><A
HREF="r2555.html"
>fann_create</A
> -- Creates an artificial neural network.</DT
><DT
><A
HREF="r2597.html"
>fann_train</A
> -- Train an artificial neural network.</DT
><DT
><A
HREF="r2641.html"
>fann_save</A
> -- Save an artificial neural network to a file.</DT
><DT
><A
HREF="r2664.html"
>fann_run</A
> -- Run an artificial neural network.</DT
><DT
><A
HREF="r2688.html"
>fann_randomize_weights</A
> -- Randomize the weights of the neurons in the network.</DT
><DT
><A
HREF="r2714.html"
>fann_init_weights</A
> -- Initialize the weight of each connection.</DT
><DT
><A
HREF="r2740.html"
>fann_get_MSE</A
> -- Get the mean squared error.</DT
><DT
><A
HREF="r2756.html"
>fann_get_num_input</A
> -- Get the number of input neurons.</DT
><DT
><A
HREF="r2777.html"
>fann_get_num_output</A
> -- Get the number of output neurons.</DT
><DT
><A
HREF="r2798.html"
>fann_get_total_neurons</A
> -- Get the total number of neurons.</DT
><DT
><A
HREF="r2819.html"
>fann_get_total_connections</A
> -- Get the total number of connections.</DT
><DT
><A
HREF="r2835.html"
>fann_get_learning_rate</A
> -- Get the learning rate.</DT
><DT
><A
HREF="r2854.html"
>fann_get_activation_function_hidden</A
> -- Get the activation function of the hidden neurons.</DT
><DT
><A
HREF="r2873.html"
>fann_get_activation_function_output</A
> -- Get the activation function of the output neurons.</DT
><DT
><A
HREF="r2892.html"
>fann_get_activation_steepness_hidden</A
> -- Get the steepness of the activation function for the hidden neurons.</DT
><DT
><A
HREF="r2911.html"
>fann_get_activation_steepness_output</A
> -- Get the steepness of the activation function for the output neurons.</DT
><DT
><A
HREF="r2930.html"
>fann_set_learning_rate</A
> -- Set the learning rate.</DT
><DT
><A
HREF="r2949.html"
>fann_set_activation_function_hidden</A
> -- Set the activation function for the hidden neurons.</DT
><DT
><A
HREF="r2971.html"
>fann_set_activation_function_output</A
> -- Set the activation function for the output neurons.</DT
><DT
><A
HREF="r2993.html"
>fann_set_activation_steepness_hidden</A
> -- Set the steepness of the activation function for the hidden neurons.</DT
><DT
><A
HREF="r3015.html"
>fann_set_activation_steepness_output</A
> -- Set the steepness of the activation function for the output neurons.</DT
></DL
></DD
></DL
></DD
><DT
>7. <A
HREF="c3037.html"
>Python Bindings</A
></DT
><DD
><DL
><DT
>7.1. <A
HREF="c3037.html#python.install"
>Python Install</A
></DT
></DL
></DD
><DT
><A
HREF="b3048.html"
>Bibliography</A
></DT
></DL
></DIV
><DIV
CLASS="LOT"
><DL
CLASS="LOT"
><DT
><B
>List of Examples</B
></DT
><DT
>1-1. <A
HREF="x68.html#example.simple_train"
>Simple training example</A
></DT
><DT
>1-2. <A
HREF="x68.html#example.simple_exec"
>Simple execution example</A
></DT
><DT
>2-1. <A
HREF="x161.html#example.train_on_file_internals"
>The internals of the <CODE
CLASS="function"
>fann_train_on_file</CODE
> function, without writing the status line.</A
></DT
><DT
>2-2. <A
HREF="x161.html#example.calc_mse"
>Test all of the data in a file and calculates the mean square error.</A
></DT
><DT
>3-1. <A
HREF="c189.html#example.train_fixed"
>An example of a program written to support training in both fixed point and floating point numbers</A
></DT
><DT
>3-2. <A
HREF="x203.html#example.exec_fixed"
>An example of a program written to support both fixed point and floating point numbers</A
></DT
><DT
>5-1. <A
HREF="r285.html#example.api.fann_create_array"
><CODE
CLASS="function"
>fann_create_array</CODE
> example</A
></DT
><DT
>6-1. <A
HREF="r2555.html#example.php.fann_create.scratch"
><CODE
CLASS="function"
>fann_create</CODE
> from scratch</A
></DT
><DT
>6-2. <A
HREF="r2555.html#example.php.fann_create.load"
><CODE
CLASS="function"
>fann_create</CODE
> loading from a file</A
></DT
><DT
>6-1. <A
HREF="r2597.html#example.php.fann_train"
><CODE
CLASS="function"
>fann_create</CODE
> from training data</A
></DT
><DT
>6-1. <A
HREF="r2664.html#example.php.fann_run"
><CODE
CLASS="function"
>fann_run</CODE
>Example</A
></DT
></DL
></DIV
></DIV
><DIV
CLASS="NAVFOOTER"
><HR
ALIGN="LEFT"
WIDTH="100%"><TABLE
SUMMARY="Footer navigation table"
WIDTH="100%"
BORDER="0"
CELLPADDING="0"
CELLSPACING="0"
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
> </TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
> </TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
><A
HREF="c13.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
> </TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
> </TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Introduction</TD
></TR
></TABLE
></DIV
></BODY
></HTML
>
|
By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.
If a file you wish to view isn't highlighted, and is a text file (not binary), please
let us know and we'll add colourisation support for it.