

.. _sphx_glr_auto_examples_neural_networks:

.. _neural_network_examples:

Neural Networks
-----------------------

Examples concerning the :mod:`sklearn.neural_network` module.



.. raw:: html

    <div class="sphx-glr-thumbnails">

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This example visualizes some training loss curves for different stochastic learning strategies, including SGD and Adam. Because of time-constraints, we use several small datasets, for which L-BFGS might be more suitable. The general trend shown in these examples seems to carry over to larger datasets, however.">

.. only:: html

  .. image:: /auto_examples/neural_networks/images/thumb/sphx_glr_plot_mlp_training_curves_thumb.png
    :alt:

  :doc:`/auto_examples/neural_networks/plot_mlp_training_curves`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Compare Stochastic learning strategies for MLPClassifier</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="For greyscale image data where pixel values can be interpreted as degrees of blackness on a white background, like handwritten digit recognition, the Bernoulli Restricted Boltzmann machine model (BernoulliRBM) can perform effective non-linear feature extraction.">

.. only:: html

  .. image:: /auto_examples/neural_networks/images/thumb/sphx_glr_plot_rbm_logistic_classification_thumb.png
    :alt:

  :doc:`/auto_examples/neural_networks/plot_rbm_logistic_classification`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Restricted Boltzmann Machine features for digit classification</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="A comparison of different values for regularization parameter &#x27;alpha&#x27; on synthetic datasets. The plot shows that different alphas yield different decision functions.">

.. only:: html

  .. image:: /auto_examples/neural_networks/images/thumb/sphx_glr_plot_mlp_alpha_thumb.png
    :alt:

  :doc:`/auto_examples/neural_networks/plot_mlp_alpha`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Varying regularization in Multi-layer Perceptron</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Sometimes looking at the learned coefficients of a neural network can provide insight into the learning behavior. For example if weights look unstructured, maybe some were not used at all, or if very large coefficients exist, maybe regularization was too low or the learning rate too high.">

.. only:: html

  .. image:: /auto_examples/neural_networks/images/thumb/sphx_glr_plot_mnist_filters_thumb.png
    :alt:

  :doc:`/auto_examples/neural_networks/plot_mnist_filters`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Visualization of MLP weights on MNIST</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/neural_networks/plot_mlp_training_curves
   /auto_examples/neural_networks/plot_rbm_logistic_classification
   /auto_examples/neural_networks/plot_mlp_alpha
   /auto_examples/neural_networks/plot_mnist_filters

