multihead_attention_layer.h File Reference

Declares the MultiHeadAttention layer used in Transformer-style encoders and decoders. More...

#include "layer.h"
#include "operators.h"
#include "math_utilities.h"
#include "forward_propagation.h"
#include "back_propagation.h"

Go to the source code of this file.

Classes
class	opennn::MultiHeadAttention
	Scaled dot-product attention with multiple heads and learned linear projections. More...

Namespaces
namespace	opennn

Detailed Description

Declares the MultiHeadAttention layer used in Transformer-style encoders and decoders.