:orphan:

Examples
========

Runnable examples with generated output and plots.
Each script can also be downloaded as a Jupyter notebook.



.. raw:: html

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

.. thumbnail-parent-div-open

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Fit a single-model AMICA (equivalent to Infomax ICA) on synthetic data. Inspects the raw input, convergence via the log-likelihood curve, and confirms that the sphering matrix correctly whitens the data.">

.. only:: html

  .. image:: /_generated/examples/images/thumb/sphx_glr_plot_basic_fit_thumb.png
    :alt:

  :doc:`/_generated/examples/plot_basic_fit`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Basic AMICA Fit</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="ICA finds components that are as statistically independent as possible. This example demonstrates that property directly: we generate 8 truly independent Laplacian sources, mix them linearly, then show how both AMICA and extended Infomax reduce the pairwise mutual information (MI) between the recovered components compared to the original mixed channels.">

.. only:: html

  .. image:: /_generated/examples/images/thumb/sphx_glr_plot_mutual_information_thumb.png
    :alt:

  :doc:`/_generated/examples/plot_mutual_information`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Mutual Information Reduction</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Fit AmicaICA on synthetic EEG data with two mixture models, verify that AMICA correctly assigns each data segment to the right model, and confirm that reconstructing the signal without exclusions is a perfect round-trip.">

.. only:: html

  .. image:: /_generated/examples/images/thumb/sphx_glr_plot_mne_workflow_thumb.png
    :alt:

  :doc:`/_generated/examples/plot_mne_workflow`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">MNE-Python Workflow</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Demonstrates the full artefact-removal workflow on data with two distinct experimental conditions and blink artefacts occurring throughout both.">

.. only:: html

  .. image:: /_generated/examples/images/thumb/sphx_glr_plot_artefact_removal_thumb.png
    :alt:

  :doc:`/_generated/examples/plot_artefact_removal`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Artefact Removal with Multi-Model AMICA</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Demonstrates the do_reject feature on heavily contaminated synthetic data. AMICA identifies and excludes time points whose per-sample log-likelihood falls more than reject_sigma standard deviations below the mean, then immediately re-runs the E-step so the M-step already uses clean statistics.  Up to num_reject rejection events are allowed; after that the mask is frozen.">

.. only:: html

  .. image:: /_generated/examples/images/thumb/sphx_glr_plot_outlier_rejection_thumb.png
    :alt:

  :doc:`/_generated/examples/plot_outlier_rejection`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Outlier Rejection</div>
    </div>


.. thumbnail-parent-div-close

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /_generated/examples/plot_basic_fit
   /_generated/examples/plot_mutual_information
   /_generated/examples/plot_mne_workflow
   /_generated/examples/plot_artefact_removal
   /_generated/examples/plot_outlier_rejection



.. only:: html

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

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