https://github.com/nengo/keras-spiking

Spiking neuron integration for Keras
https://github.com/nengo/keras-spiking

deep-learning keras python spiking-neural-networks tensorflow

Last synced: about 1 month ago
JSON representation

Spiking neuron integration for Keras

• Host: GitHub
• URL: https://github.com/nengo/keras-spiking
• Owner: nengo
• License: other
• Created: 2020-08-07T13:30:55.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2024-02-28T20:12:45.000Z (10 months ago)
• Last Synced: 2024-11-08T09:09:52.157Z (about 2 months ago)
• Topics: deep-learning, keras, python, spiking-neural-networks, tensorflow
• Language: Python
• Homepage: https://www.nengo.ai/keras-spiking/
• Size: 13.1 MB
• Stars: 31
• Watchers: 7
• Forks: 2
• Open Issues: 9
• Metadata Files:
  • Readme: README.rst
  • Changelog: CHANGES.rst
  • Contributing: CONTRIBUTING.rst
  • License: LICENSE.rst

Awesome Lists containing this project

README

        
.. image:: https://img.shields.io/pypi/v/keras-spiking.svg

  :target: https://pypi.org/project/keras-spiking

  :alt: Latest PyPI version

.. image:: https://img.shields.io/pypi/pyversions/keras-spiking.svg

  :target: https://pypi.org/project/keras-spiking

  :alt: Python versions

************

KerasSpiking

************

KerasSpiking provides tools for training and running spiking neural networks

directly within the Keras framework. The main feature is

``keras_spiking.SpikingActivation``, which can be used to transform

any activation function into a spiking equivalent. For example, we can translate a

non-spiking model, such as

.. code-block:: python

    inp = tf.keras.Input((5,))

    dense = tf.keras.layers.Dense(10)(inp)

    act = tf.keras.layers.Activation("relu")(dense)

    model = tf.keras.Model(inp, act)

into the spiking equivalent:

.. code-block:: python

    # add time dimension to inputs

    inp = tf.keras.Input((None, 5))

    dense = tf.keras.layers.Dense(10)(inp)

    # replace Activation with SpikingActivation

    act = keras_spiking.SpikingActivation("relu")(dense)

    model = tf.keras.Model(inp, act)

Models with SpikingActivation layers can be optimized and evaluated in the same way as

any other Keras model. They will automatically take advantage of KerasSpiking's

"spiking aware training": using the spiking activations on the forward pass and the

non-spiking (differentiable) activation function on the backwards pass.

KerasSpiking also includes various tools to assist in the training of spiking models,

such as additional `regularizers

`_

and `filtering layers

`_.

If you are interested in building and optimizing spiking neuron models, you may also

be interested in `NengoDL `_. See

`this page `_ for a

comparison of the different use cases supported by these two packages.

**Documentation**

Check out the `documentation `_ for

- `Installation instructions

  `_

- `More detailed example introducing the features of KerasSpiking

  `_

- `API reference `_