![]() |
Neuron Net
|
Describes the forward path process for the Neuron Base. More...
Macros | |
| #define | def_k_FeedForward 0 |
| Index of FeedForward kernel. More... | |
| #define | def_k_ff_matrix_w 0 |
| Weights matrix (m+1)*n, where m - number of neurons in layer and n - number of outputs (neurons in next layer) More... | |
| #define | def_k_ff_matrix_i 1 |
| Inputs tesor. More... | |
| #define | def_k_ff_matrix_o 2 |
| Output tensor. More... | |
| #define | def_k_ff_inputs 3 |
| Number of inputs. More... | |
| #define | def_k_ff_activation 4 |
| Activation type (ENUM_ACTIVATION) More... | |
Functions | |
| __kernel void | FeedForward (__global double *matrix_w, __global double *matrix_i, __global double *matrix_o, int inputs, int activation) |
| Describes the forward path process for the Neuron Base (CNeuronBaseOCL). More... | |
| virtual bool | CNeuronBaseOCL::feedForward (CNeuronBaseOCL *NeuronOCL) |
| Feed Forward method of calling kernel FeedForward(). More... | |
Describes the forward path process for the Neuron Base.
Detailed description on the link.
| #define def_k_FeedForward 0 |
Index of FeedForward kernel.
Definition at line 90 of file NeuroNet.mqh.
| #define def_k_ff_activation 4 |
Activation type (ENUM_ACTIVATION)
Definition at line 95 of file NeuroNet.mqh.
| #define def_k_ff_inputs 3 |
Number of inputs.
Definition at line 94 of file NeuroNet.mqh.
| #define def_k_ff_matrix_i 1 |
Inputs tesor.
Definition at line 92 of file NeuroNet.mqh.
| #define def_k_ff_matrix_o 2 |
Output tensor.
Definition at line 93 of file NeuroNet.mqh.
| #define def_k_ff_matrix_w 0 |
Weights matrix (m+1)*n, where m - number of neurons in layer and n - number of outputs (neurons in next layer)
Definition at line 91 of file NeuroNet.mqh.
| __kernel void FeedForward | ( | __global double * | matrix_w, |
| __global double * | matrix_i, | ||
| __global double * | matrix_o, | ||
| int | inputs, | ||
| int | activation | ||
| ) |
Describes the forward path process for the Neuron Base (CNeuronBaseOCL).
Detailed description on the link.
| [in] | matrix_w | Weights matrix (m+1)*n, where m - number of neurons in layer and n - number of outputs (neurons in next layer) |
| [in] | matrix_i | Inputs tesor |
| [out] | matrix_o | Output tensor |
| inputs | Number of inputs | |
| activation | Activation type (ENUM_ACTIVATION) |
Definition at line 15 of file NeuroNet.cl.
|
protectedvirtual |
Feed Forward method of calling kernel FeedForward().
| NeuronOCL | Pointer to previos layer. |
Reimplemented in CNeuronAttentionOCL, CNeuronConvOCL, and CNeuronProofOCL.
Definition at line 3172 of file NeuroNet.mqh.