Simd Library Documentation.

Home | Release Notes | Download | Documentation | Forum | SourceForge | GitHub
FullyConnectedLayer Class Reference

FullyConnectedLayer class. More...

+ Inheritance diagram for FullyConnectedLayer:

Public Member Functions

 FullyConnectedLayer (Function::Type f, size_t srcSize, size_t dstSize, bool bias=true)
 Creates new FullyConnectedLayer class. More...
 
- Public Member Functions inherited from Layer
virtual ~Layer ()
 

Additional Inherited Members

- Public Types inherited from Layer
enum  Type {
  Input,
  Convolutional,
  MaxPooling,
  FullyConnected,
  Dropout
}
 
enum  Method {
  Fast,
  Check,
  Train
}
 

Detailed Description

FullyConnectedLayer class.

Fully connected layer in neural network.

Constructor & Destructor Documentation

FullyConnectedLayer ( Function::Type  f,
size_t  srcSize,
size_t  dstSize,
bool  bias = true 
)

Creates new FullyConnectedLayer class.

Parameters
[in]f- a type of activation function used in this layer.
[in]srcSize- a size of input vector.
[in]dstSize- a size of output vector.
[in]bias- a boolean flag (enabling of bias). By default it is True.