Core network library for a deep neural network. More...

#include "util/mnist-utils.h"
#include "util/mnist-stats.h"

Data Structures
struct	Volume
	Data structure defining a 3-dimensional vector used to define the size of a node map. More...

struct	LayerDefinition
	Data structure allowing users to define the characteristics of a network. More...

struct	Connection
	Data structure attached to a node and pointing to another node as well as to a weight. More...

struct	Node
	Variably-sized data structure modeling a neuron with a variable number of connections/weights. More...

struct	Column
	Variably-sized data structure modeling a vector of nodes. More...

struct	Layer
	Variably-sized data structure holding a definable number of columns that form a layer. More...

struct	Network
	Variably-sized data structure that serves as the over container for a whole network. More...

Macros
#define	MAX_CONVOLUTIONAL_FILTER 10

Typedefs
typedef struct LayerDefinition	LayerDefinition

typedef struct Vector3D	Vector3D

typedef struct Value2D	Value2D

typedef struct Volume	Volume

typedef struct Network	Network

typedef struct Layer	Layer

typedef struct Column	Column

typedef struct Node	Node

typedef struct Connection	Connection

typedef double	Weight

typedef unsigned long	ByteSize

typedef enum LayerType	LayerType

typedef enum ActFctType	ActFctType

Enumerations
enum	LayerType { EMPTY, INPUT, CONVOLUTIONAL, FULLY_CONNECTED, OUTPUT }

enum	ActFctType { SIGMOID, TANH, RELU, NONE }

Functions
int	getLayerNodeCount (LayerDefinition *layerDef)
	Returns the number of nodes in a layer. More...

int	getNodeBackwardConnectionCount (LayerDefinition *layerDef)
	Returns the number of backward connections of a NODE (not of a layer) More...

int	getLayerWeightCount (LayerDefinition *layerDef)
	Returns the number of weights for a layer (based on a given layer definition) More...

ByteSize	getLayerWeightBlockSize (LayerDefinition *layerDef)
	Returns the memory (byte) size of the weights block for a specific layer. More...

ByteSize	getLayerSize (LayerDefinition *layerDef)
	Returns the memory (byte) size of a specific layer based on a given layer definition. More...

int	calcStride (int tgtWidth, int filter, int srcWidth)
	Calculates the stride (number of nodes/columns that are skipped) in a convolutional kernel. More...

void	feedInput (Network nn, Vector v)
	Feeds some Vector data into the INPUT layer of the network. More...

void	feedForwardNetwork (Network *nn)
	Feeds forward (=calculating a node's output value and applying an activation function) layer by layer. More...

void	backPropagateNetwork (Network *nn, int targetClassification)
	Backpropagates the output nodes' errors from output layer backwards to first layer. More...

int	getNetworkClassification (Network *nn)
	Returns the network's classification of the input image by choosing the node with the hightest output. More...

Network *	createNetwork (int layerCount, LayerDefinition *layerDefs)
	Creates the neural network based on a given array of layer definitions. More...

LayerDefinition *	setLayerDefinitions (int layerCount,...)
	Returns a pointer to an array of a variable number of layer definitions. More...

Detailed Description

Core network library for a deep neural network.

Author: Matt Lind

Date: February 2016

Macro Definition Documentation

#define MAX_CONVOLUTIONAL_FILTER 10

Typedef Documentation

typedef enum ActFctType ActFctType

typedef unsigned long ByteSize

typedef struct Column Column

typedef struct Connection Connection

typedef struct Layer Layer

typedef struct LayerDefinition LayerDefinition

typedef enum LayerType LayerType

typedef struct Network Network

typedef struct Node Node

typedef struct Value2D Value2D

typedef struct Vector3D Vector3D

typedef struct Volume Volume

typedef double Weight

Enumeration Type Documentation

enum ActFctType

Enumerator
SIGMOID
TANH
RELU
NONE

enum LayerType

Enumerator
EMPTY
INPUT
CONVOLUTIONAL
FULLY_CONNECTED
OUTPUT

Function Documentation

void backPropagateNetwork	(	Network *	nn,
		int	targetClassification
	)

Backpropagates the output nodes' errors from output layer backwards to first layer.

The network's backpropagation proceeds in 2 steps:

CALCULATE OUTPUT NODES' ERRORS a. Calculate the errorsums in all output cells based on the targetClassification
BACKPROPAGATE EACH LAYER a. Update the nodes weights based on actual output and accumulated errorsum b. Calculate the errorsums in all TARGET cells based on errorsum in this layer (calculated in 3)

Parameters

nn	A pointer to the neural network
targetClassification	The correct/desired classification (=label) of this recognition/image

int calcStride	(	int	tgtWidth,
		int	filter,
		int	srcWidth
	)

Calculates the stride (number of nodes/columns that are skipped) in a convolutional kernel.

Parameters

tgtWidth	Number of columns on the x-axis (horizontally) in the TARGET (=previous) layer
filter	Number of columns/nodes on the x-axis in a filter window (

Attention: ASSSUMES WIDTH=HEIGHT!!)

Parameters

srcWidth Number of columns on the x-axis (horizontally) in the SOURCE (=this) layer

Network* createNetwork	(	int	layerCount,
		LayerDefinition *	layerDefs
	)

Creates the neural network based on a given array of layer definitions.

Creates a reserved memory block for this network based on the given layer definitions, and then initializes this memory with the respective layer/node/connection/weights structure.

Parameters

layerCount	The number of layer definitions inside the layer-definition-array (2nd param)
layerDefs	A pointer to an array of layer definitions

void feedForwardNetwork ( Network * nn )

Feeds forward (=calculating a node's output value and applying an activation function) layer by layer.

Feeds forward from 2nd=#1 layer (i.e. skips input layer) to output layer

Parameters

nn	A pointer to the NN

void feedInput	(	Network *	nn,
		Vector *	v
	)

Feeds some Vector data into the INPUT layer of the network.

Parameters

nn	A pointer to the neural network
v	A pointer to the vector holding the input values

int getLayerNodeCount ( LayerDefinition * layerDef )

Returns the number of nodes in a layer.

Parameters

layerDef Pointer to a layer definition

ByteSize getLayerSize ( LayerDefinition * layerDef )

Returns the memory (byte) size of a specific layer based on a given layer definition.

Each layer's memory size may be different due to a different number of nodes and connections For FEED FORWARD (e.g. OUTPUT) layers, full connectivity is assumed (i.e. each node links to ALL nodes in the previous layer)

Parameters

layerDef A pointer to a layer definition

ByteSize getLayerWeightBlockSize ( LayerDefinition * layerDef )

Returns the memory (byte) size of the weights block for a specific layer.

Each layer's number of weights may be different due to a different number of connections For FEED FORWARD (HIDDEN and OUTPUT) layers, full connectivity is assumed, CONV layers e.g. share weights.

Parameters

layerDef A pointer to a layer definition

int getLayerWeightCount ( LayerDefinition * layerDef )

Returns the number of weights for a layer (based on a given layer definition)

Parameters

layerDef A pointer to the layer definition

int getNetworkClassification ( Network * nn )

Returns the network's classification of the input image by choosing the node with the hightest output.

Parameters

nn	A pointer to the neural network

int getNodeBackwardConnectionCount ( LayerDefinition * layerDef )

Returns the number of backward connections of a NODE (not of a layer)

For FEED FORWARD (HIDDEN and OUTPUT) layers, full connectivity is assumed (each node links to ALL nodes in the previous layer)

Parameters

layerDef Pointer to a layer definition

LayerDefinition* setLayerDefinitions	(	int	layerCount,
			...
	)

Returns a pointer to an array of a variable number of layer definitions.

Parameters

layerCount	Number of layers of the network
...	Variabe number of layer definition objects

Data Structures

Macros

Typedefs

Enumerations

Functions

Detailed Description

Macro Definition Documentation

Typedef Documentation

Enumeration Type Documentation

Function Documentation