📄 r1597.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN""http://www.w3.org/TR/html4/loose.dtd"><HTML><HEAD><TITLE>struct fann</TITLE><link href="../style.css" rel="stylesheet" type="text/css"><METANAME="GENERATOR"CONTENT="Modular DocBook HTML Stylesheet Version 1.79"><LINKREL="HOME"TITLE="Fast Artificial Neural Network Library"HREF="index.html"><LINKREL="UP"TITLE="Data Structures"HREF="x1595.html"><LINKREL="PREVIOUS"TITLE="Data Structures"HREF="x1595.html"><LINKREL="NEXT"TITLE="struct fann_train_data"HREF="r1837.html"></HEAD><BODYCLASS="refentry"BGCOLOR="#FFFFFF"TEXT="#000000"LINK="#0000FF"VLINK="#840084"ALINK="#0000FF"><DIVCLASS="NAVHEADER"><TABLESUMMARY="Header navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><THCOLSPAN="3"ALIGN="center">Fast Artificial Neural Network Library</TH></TR><TR><TDWIDTH="10%"ALIGN="left"VALIGN="bottom"><AHREF="x1595.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="80%"ALIGN="center"VALIGN="bottom"></TD><TDWIDTH="10%"ALIGN="right"VALIGN="bottom"><AHREF="r1837.html"ACCESSKEY="N">Next</A></TD></TR></TABLE><HRALIGN="LEFT"WIDTH="100%"></DIV><H1><ANAME="api.struct.fann"></A>struct fann</H1><DIVCLASS="refnamediv"><ANAME="AEN1598"></A><H2>Name</H2>struct fann -- Describes a neural network.</DIV><DIVCLASS="refsect1"><ANAME="AEN1601"></A><H2>Description</H2><P> This structure is subject to change at any time. If you need to use the values contained herein, please see the <AHREF="x938.html">Options</A> functions. If these functions do not fulfill your needs, please open a feature request on our SourceForge <AHREF="http://www.sourceforge.net/projects/fann"TARGET="_top">project page</A>. </P><P></P><DIVCLASS="variablelist"><P><B>Properties</B></P><DL><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">errno_f</CODE></DT><DD><P>The type of error that last occurred.</P></DD><DT><SPANCLASS="type">FILE *</SPAN> <CODECLASS="varname">error_log</CODE></DT><DD><P>Where to log error messages.</P></DD><DT><SPANCLASS="type">char *</SPAN> <CODECLASS="varname">errstr</CODE></DT><DD><P>A string representation of the last error.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">learning_rate</CODE></DT><DD><P>The learning rate of the network.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">connection_rate</CODE></DT><DD><P>The connection rate of the network. Between 0 and 1, 1 meaning fully connected.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">shortcut_connections</CODE></DT><DD><P> Is 1 if shortcut connections are used in the ann otherwise 0 Shortcut connections are connections that skip layers. A fully connected ann with shortcut connections is an ann where neurons have connections to all neurons in all later layers. </P><P> ANNs with shortcut connections are created by <AHREF="r315.html"><CODECLASS="function">fann_create_shortcut</CODE></A>. </P></DD><DT><SPANCLASS="type">struct fann_layer *</SPAN> <CODECLASS="varname">first_layer</CODE></DT><DD><P> Pointer to the first layer (input layer) in an array of all the layers, including the input and output layer. </P></DD><DT><SPANCLASS="type">struct fann_layer *</SPAN> <CODECLASS="varname">last_layer</CODE></DT><DD><P> Pointer to the layer past the last layer in an array of all the layers, including the input and output layer. </P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">total_neurons</CODE></DT><DD><P> Total number of neurons. Very useful, because the actual neurons are allocated in one long array. </P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">num_input</CODE></DT><DD><P>Number of input neurons (not calculating bias)</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">num_output</CODE></DT><DD><P>Number of output neurons (not calculating bias)</P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">train_errors</CODE></DT><DD><P> Used to contain the error deltas used during training Is allocated during first training session, which means that if we do not train, it is never allocated. </P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">activation_function_output</CODE></DT><DD><P>Used to choose which activation function to use in the output layer.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">activation_function_hidden</CODE></DT><DD><P>Used to choose which activation function to use in the hidden layers.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">activation_steepness_hidden</CODE></DT><DD><P>Parameters for the activation function in the hidden layers.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">activation_steepness_output</CODE></DT><DD><P>Parameters for the activation function in the output layer.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">training_algorithm</CODE></DT><DD><P> Training algorithm used when calling fann_train_on_... and <AHREF="r685.html"><CODECLASS="function">fann_train_epoch</CODE></A>. </P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">decimal point</CODE></DT><DD><P> <SPANCLASS="emphasis"><ICLASS="emphasis">Fixed point only.</I></SPAN> The decimal point, used for shifting the fix point in fixed point integer operations.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">multiplier</CODE></DT><DD><P> <SPANCLASS="emphasis"><ICLASS="emphasis">Fixed point only.</I></SPAN> The multiplier, used for multiplying the fix point in fixed point integer operations. Only used in special cases, since the decimal_point is much faster. </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">activation_results_hidden</CODE></DT><DD><P> An array of six members used by some activation functions to hold results for the hidden layer(s). </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">activation_values_hidden</CODE></DT><DD><P> An array of six members used by some activation functions to hold values for the hidden layer(s). </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">activation_results_output</CODE></DT><DD><P> An array of six members used by some activation functions to hold results for the output layer. </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">activation_values_output</CODE></DT><DD><P> An array of six members used by some activation functions to hold values for the output layer. </P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">total_connections</CODE></DT><DD><P> Total number of connections. Very useful, because the actual connections are allocated in one long array. </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">output</CODE></DT><DD><P>Used to store outputs in.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">num_MSE</CODE></DT><DD><P>The number of data used to calculate the mean square error.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">MSE_value</CODE></DT><DD><P>The total error value. The real mean square error is MSE_value/num_MSE.</P></DD><DT><SPANCLASS="type">unsigned int</SPAN> <CODECLASS="varname">train_error_function</CODE></DT><DD><P>When using this, training is usually faster. Makes the error used for calculating the slopes higher when the difference is higher. </P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">quickprop_decay</CODE></DT><DD><P>Decay is used to make the weights not go so high.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">quickprop_mu</CODE></DT><DD><P>Mu is a factor used to increase and decrease the step-size.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">rprop_increase_factor</CODE></DT><DD><P>Tells how much the step-size should increase during learning.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">rprop_decrease_factor</CODE></DT><DD><P>Tells how much the step-size should decrease during learning.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">rprop_delta_min</CODE></DT><DD><P>The minimum step-size.</P></DD><DT><SPANCLASS="type">float</SPAN> <CODECLASS="varname">rprop_delta_max</CODE></DT><DD><P>The maximum step-size.</P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">train_slopes</CODE></DT><DD><P> Used to contain the slope errors used during batch training Is allocated during first training session, which means that if we do not train, it is never allocated. </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">prev_steps</CODE></DT><DD><P> The previous step taken by the quickprop/rprop procedures. Not allocated if not used. </P></DD><DT><SPANCLASS="type">fann_type *</SPAN> <CODECLASS="varname">prev_train_slopes</CODE></DT><DD><P> The slope values used by the quickprop/rprop procedures. Not allocated if not used. </P></DD></DL></DIV></DIV><DIVCLASS="NAVFOOTER"><HRALIGN="LEFT"WIDTH="100%"><TABLESUMMARY="Footer navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top"><AHREF="x1595.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="index.html"ACCESSKEY="H">Home</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top"><AHREF="r1837.html"ACCESSKEY="N">Next</A></TD></TR><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top">Data Structures</TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="x1595.html"ACCESSKEY="U">Up</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top">struct fann_train_data</TD></TR></TABLE></DIV></BODY></HTML>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -