MAS
============

Memory Aware Synapses (MAS) is a regularization-based continual learning method that computes the importance of parameters according to how sensitive the parameters are.
For the details, see the `original paper <https://arxiv.org/pdf/1711.09601.pdf>`_.

Node-level Problems
-------------------------

.. automodule:: begin.algorithms.mas.nodes
    :undoc-members:
    :members:
    :private-members:

Link-level Problems
-------------------------

.. automodule:: begin.algorithms.mas.links
    :undoc-members:
    :members:
    :private-members:

Graph-level Problems
-------------------------

.. automodule:: begin.algorithms.mas.graphs
    :undoc-members:
    :members:
    :private-members: