MCPN Namespace Reference

Main namespace of Multi-Core Optimized Perceptron Network library. More...

Classes
class	Activation_Functions
	Activation functions applied to neurons of the whole layer. Per-neuron activation function setting is not supported. More...
class	Binary_Stream_To_Text
	This class provides methods to operate with configuration stream containing textual data as if it was binary data stream. More...
class	Configuration_Stream_Converter
	Class is used to convert streams containing network configuration from text to binary and vice-versa. More...
class	File_Stream
	A template class to work with files using Simple_Stream interface. Please note that class works in 2 modes: read and append (in latter case creates file if non-existent). Mode of operation is determined based on first method called: if Read() was called first then mode is set to read, in case of Write() call, append mode is selected. More...
struct	Range
	Structure representing a range of numbers. More...
class	Raw_Data_Reader
	Reads binary data from a stream into std::vector<double>, stops when there is no more data in the stream. More...
class	Data_Set_Interpreter
	Turns vector<double> into a collection of training samples, this is only a base class, no relevant implementation. More...
class	Sequential_Diffs_Interpreter
	Interprets dataset as a continuous sequence of result values of a certain function y = f(x,..). Each sample is created by a sliding window of size = number of inputs + number of outputs. Window is shifting 1 value towards the end of the set at a time. Example: network has 3 inputs and 2 outputs, set contains 7 values which totals in 3 available samples. More...
class	Sequential_Diffs_No_Repeat_Interpreter
	Interprets dataset as a continuous sequence of result values of a certain function y = f(x,..). Each sample is created by a sliding window of size = number of inputs + number of outputs. Window is shifting "size" values towards the end of the set at a time. Example: network has 3 inputs and 2 outputs, set contains 10 values which totals in 2 available samples. More...
class	Layers_Processor
	The main processing class of a neural network. Performs calculations for all layers. More...
class	Memory_Stream
	Provides possibility to work with memory buffer through a Simple_Stream interface. Please note that Read and Write operations both increment internal pointer (in the same way as file operations). If the end of buffer is reached operations will not fail - only return less bytes (or zero) than required by Read or Write. More...
class	Mutex
	A synchronization primitive for multithreaded applications. Multiple Get() method calls from one process will not lead to deadlock, in other words the mutex is reentrant. More...
class	Neural_Net
	The core class of MCPN library, neural network itself. More...
class	Semaphore
	A synchronization primitive for multithreaded applications. Multiple Get() method calls from one process will deadlock the calling process, this is the main difference from Mutex. More...
class	Self_Lock
	An artificial thread deadlock at user disposal. Using Seal(int key_count) method caller causes calling thread to deadlock and wait until the deadlock situation is resolved by other process(es) calling Release() method key_count number of times. More...
class	Simple_Stream
	Template based Stream interface that provides only most necessary methods. More...
class	Spin_Lock
	A synchronization primitive for multithreaded applications. Multiple Get() method calls from one process will lead to deadlock, in other words the Spin_Lock is non-reentrant. Thread will not suspend waiting for resource but will "spin". More...
class	Spin_Mutex
	A synchronization primitive for multithreaded applications. Multiple Get() method calls from one process will not lead to deadlock, in other words the Spin_Mutex is reentrant. Thread will not suspend waiting for resource but will "spin". More...
class	Trainer
	Class that makes training a network easier. It uses a special stop strategy object to decide when training is complete. Trainer class creates a network configuration that is optimal according to the used stop training strategy. More...
class	Stop_Training_Strategy
	Sole purpose of this class is to determine when the training should be stopped. This is only a base with a pure virtual method should_stop to be implemented in child classes. Stop strategies are friends of Trainer class. More...
class	Epoch_Based_Stop_Strategy
	Training will stop after N epochs (specified on construction) are passed. More...
class	MSE_Based_Stop_Strategy
	Training will stop when Mean Squared Error will stop decreasing. More...
class	Weights_Initializer
	Implements the following algorithm: "Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights" by Derrick Nguyen and Bernard Widrow. More...
Functions
double	fast_exp (const double arg)
	High performance exponent function implementation according to "A Fast, Compact Approximation of the Exponential Function" by Nicol N. Schraudolph, Technical Report IDSIA-07-98.
bool	float_equal (double x, double y, double precision=0.0001)
	Checking floating point values for equity with "==" usually gives incorrect results. This function will take values you want to check and a precision value that shows what maximum difference between those values is allowed for them to still be considered equal.
bool	convert_value (double &value, const Range &from, const Range &to)
	Converts value from source range into value from destination range.
bool	text_to_int (const char *buf, const size_t len, int *out)
	Converts text buffer (0-terminator not needed) of given size to int.
bool	text_to_double (const char *buf, const size_t len, double *out)
	Converts text buffer (0-terminator not needed) of given size to double.
bool	is_text (const char *buf, const size_t len)
	Performs a check if all chars in the buffer are printable (result is false if even 1 char is not printable).
int	trace (const char *format,...)
	Outputs trace (output destination depends on implementation), supports formatted output printf() style.

---

Detailed Description

Main namespace of Multi-Core Optimized Perceptron Network library.