.. note::
    :class: sphx-glr-download-link-note

    Click :ref:`here <sphx_glr_download_auto_examples_neural_networks_plot_mnist_filters.py>` to download the full example code
.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_neural_networks_plot_mnist_filters.py:


=====================================
Visualization of MLP weights on MNIST
=====================================

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.

This example shows how to plot some of the first layer weights in a
MLPClassifier trained on the MNIST dataset.

The input data consists of 28x28 pixel handwritten digits, leading to 784
features in the dataset. Therefore the first layer weight matrix have the shape
(784, hidden_layer_sizes[0]).  We can therefore visualize a single column of
the weight matrix as a 28x28 pixel image.

To make the example run faster, we use very few hidden units, and train only
for a very short time. Training longer would result in weights with a much
smoother spatial appearance.




.. code-block:: pytb

    Traceback (most recent call last):
      File "/build/scikit-learn-0.20.0+dfsg/examples/neural_networks/plot_mnist_filters.py", line 30, in <module>
        X, y = fetch_openml('mnist_784', version=1, return_X_y=True)
      File "/build/scikit-learn-0.20.0+dfsg/.pybuild/cpython3_3.6/build/sklearn/datasets/openml.py", line 449, in fetch_openml
        data_home = get_data_home(data_home=data_home)
      File "/build/scikit-learn-0.20.0+dfsg/.pybuild/cpython3_3.6/build/sklearn/datasets/base.py", line 56, in get_data_home
        makedirs(data_home)
      File "/usr/lib/python3.6/os.py", line 210, in makedirs
        makedirs(head, mode, exist_ok)
      File "/usr/lib/python3.6/os.py", line 220, in makedirs
        mkdir(name, mode)
    PermissionError: [Errno 13] Permission denied: '/nonexistent'





.. code-block:: python

    import matplotlib.pyplot as plt
    from sklearn.datasets import fetch_openml
    from sklearn.neural_network import MLPClassifier

    print(__doc__)

    # Load data from https://www.openml.org/d/554
    X, y = fetch_openml('mnist_784', version=1, return_X_y=True)
    X = X / 255.

    # rescale the data, use the traditional train/test split
    X_train, X_test = X[:60000], X[60000:]
    y_train, y_test = y[:60000], y[60000:]

    # mlp = MLPClassifier(hidden_layer_sizes=(100, 100), max_iter=400, alpha=1e-4,
    #                     solver='sgd', verbose=10, tol=1e-4, random_state=1)
    mlp = MLPClassifier(hidden_layer_sizes=(50,), max_iter=10, alpha=1e-4,
                        solver='sgd', verbose=10, tol=1e-4, random_state=1,
                        learning_rate_init=.1)

    mlp.fit(X_train, y_train)
    print("Training set score: %f" % mlp.score(X_train, y_train))
    print("Test set score: %f" % mlp.score(X_test, y_test))

    fig, axes = plt.subplots(4, 4)
    # use global min / max to ensure all weights are shown on the same scale
    vmin, vmax = mlp.coefs_[0].min(), mlp.coefs_[0].max()
    for coef, ax in zip(mlp.coefs_[0].T, axes.ravel()):
        ax.matshow(coef.reshape(28, 28), cmap=plt.cm.gray, vmin=.5 * vmin,
                   vmax=.5 * vmax)
        ax.set_xticks(())
        ax.set_yticks(())

    plt.show()

**Total running time of the script:** ( 0 minutes  0.000 seconds)


.. _sphx_glr_download_auto_examples_neural_networks_plot_mnist_filters.py:


.. only :: html

 .. container:: sphx-glr-footer
    :class: sphx-glr-footer-example



  .. container:: sphx-glr-download

     :download:`Download Python source code: plot_mnist_filters.py <plot_mnist_filters.py>`



  .. container:: sphx-glr-download

     :download:`Download Jupyter notebook: plot_mnist_filters.ipynb <plot_mnist_filters.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.readthedocs.io>`_
