# {py:mod}`evox.problems.neuroevolution.supervised_learning`

```{py:module} evox.problems.neuroevolution.supervised_learning
```

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning
:allowtitles:
```

## Module Contents

### Classes

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`SupervisedLearningProblem <evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem>`
  - ```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem
    :summary:
    ```
````

### API

`````{py:class} SupervisedLearningProblem(model: torch.nn.Module, data_loader: torch.utils.data.DataLoader, criterion: torch.nn.Module, n_batch_per_eval: int = 1, pop_size: int | None = None, device: torch.device | None = None, reduction: str = 'mean')
:canonical: evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem

Bases: {py:obj}`evox.core.Problem`

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem
```

```{rubric} Initialization
```

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem.__init__
```

````{py:method} _vmap_forward_pass(model_state: typing.Tuple[typing.Dict[str, torch.Tensor], typing.Dict[str, torch.Tensor]], data: typing.Tuple[torch.Tensor, torch.Tensor])
:canonical: evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._vmap_forward_pass

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._vmap_forward_pass
```

````

````{py:method} _forward_pass(model_state: typing.Tuple[typing.Dict[str, torch.Tensor], typing.Dict[str, torch.Tensor]], data: typing.Tuple[torch.Tensor, torch.Tensor])
:canonical: evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._forward_pass

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._forward_pass
```

````

````{py:method} _vmap_evaluate(pop_params: typing.Dict[str, torch.nn.Parameter])
:canonical: evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._vmap_evaluate

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._vmap_evaluate
```

````

````{py:method} _single_evaluate(params: typing.Dict[str, torch.nn.Parameter])
:canonical: evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._single_evaluate

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem._single_evaluate
```

````

````{py:method} evaluate(pop_params: typing.Dict[str, torch.nn.Parameter]) -> torch.Tensor
:canonical: evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem.evaluate

```{autodoc2-docstring} evox.problems.neuroevolution.supervised_learning.SupervisedLearningProblem.evaluate
```

````

`````