![]() |
AIfES 2 2.0.0
|
Base loss implementation of the Mean Squared Error (MSE) loss. More...
Go to the source code of this file.
Data Structures | |
struct | ailoss_mse |
General Mean Squared Error (MSE) loss struct. More... | |
Typedefs | |
typedef struct ailoss_mse | ailoss_mse_t |
New data type name for code reduction. | |
Functions | |
ailoss_t * | ailoss_mse (ailoss_mse_t *loss, ailayer_t *input_layer) |
Initialize and connect the given MSE loss. More... | |
void | ailoss_mse_calc_delta (ailoss_t *self, const aitensor_t *target_data) |
Calculate the derivative of the given MSE loss for error backpropagation. More... | |
void | ailoss_mse_calc_loss (ailoss_t *self, const aitensor_t *target_data, void *result) |
Calculate the MSE loss on the given target data. More... | |
void | ailoss_mse_print_specs (const ailoss_t *self) |
Print the loss specification. More... | |
Variables | |
const aicore_losstype_t * | ailoss_mse_type |
Mean Squared Error loss type. More... | |
Base loss implementation of the Mean Squared Error (MSE) loss.
AIfES is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License along with this program. If not, see https://www.gnu.org/licenses/.
This is an "abstract" data-type independent implementation. To use the loss, use one of the provided implementations for a specific hardware and data-type (for example from ailoss_mse_default.h) or set the required math functions on your own.
The Mean Squared Error (MSE) loss ist best suitable for regression tasks. The loss / cost is calculated as
\[ L(y, \hat{y}) = \sum_{i=0}^{N} (y_i - \hat{y}_i)^2 \]
with the predicted values \( \hat{y}_i \) and the target values \( y_i \). \( N \) is the number of elements of the \( y \) tensor.
To get the "mean" normalization, you have to modify the learning rate to \( lr = \frac {1}{o \cdot n} \cdot lr \) with the number of outputs \( o \) and the batch size \( n \).
The loss can be calculated with ailoss_mse_calc_loss(). For training the deltas /errors on the target data are calculated with ailoss_mse_calc_delta() and written to the deltas tensor of the connection layer.
ailoss_t * ailoss_mse | ( | ailoss_mse_t * | loss, |
ailayer_t * | input_layer | ||
) |
Initialize and connect the given MSE loss.
This function represents the "constructor" of the abstract MSE loss. It initializes the loss structure and connects it to the output layer of the AIfES model.
This function is not intended to call it directly. Instead use one of the data type specific implementations (like for example ailoss_mse_f32_default()).
*loss | The loss to initialize. |
*input_layer | The output layer of the model that provides the inputs to the loss. |
void ailoss_mse_calc_delta | ( | ailoss_t * | self, |
const aitensor_t * | target_data | ||
) |
Calculate the derivative of the given MSE loss for error backpropagation.
Implementation of ailoss.calc_delta.
It uses the result tensor of the output layer and the target data as input and writes the result to the deltas tensor (ailayer.deltas) of the connection layer (ailoss.connection_layer).
Calculation of the deltas:
\[ \delta_{in} \leftarrow p - y \]
\( \delta_{in} \): Result of the delta calculation of this loss (written to ailayer.deltas of the ailoss.connection_layer)
\( p \): Result of the forward pass of the output layer of the model (predicted values)
\( y \): Target data / True values / Labels
Used math functions:
*self | Loss to calculate the deltas for |
*target_data | Target data / True values / Labels |
void ailoss_mse_calc_loss | ( | ailoss_t * | self, |
const aitensor_t * | target_data, | ||
void * | result | ||
) |
Calculate the MSE loss on the given target data.
Implementation of ailoss.calc_loss.
It uses the result tensor of the output layer and the target data as input and writes the result to the given result scalar.
Calculation of the loss:
\[ result \leftarrow \sum_i (y_i - p_i)^2 \]
\( result \): Result of the loss calculation
\( p \): Result of the forward pass of the output layer of the model (predicted values)
\( y \): Target data / True values / Labels
Used math functions:
*self | Loss to calculate the deltas for |
*target_data | Target data / True values / Labels |
*result | Result scalar (the data type is specified by the data type specific implementations) |
void ailoss_mse_print_specs | ( | const ailoss_t * | self | ) |
Print the loss specification.
*self | The loss to print the specification for |
Pointer to the print function to use |
|
extern |
Mean Squared Error loss type.
Defines the type of the loss (for example for type checks and debug prints). See aicore_losstype for more information about the loss type.