The Nengo team is jubilant to announce the release of Nengo 2.7.0!
Nengo is a Python library for building and simulating large-scale neural models for AI and robotics. It can be thought of as a neural compiler, transforming a functional description of a neural model to a network of spiking or non-spiking neurons that can run on multiple backends including GPUs and neuromorphic hardware.
Nengo 2.7.0 contains a few new features and bugfixes.
We added a
SpikingRectifiedLinear neuron type,
which provides an interesting balance between
biological realism and computational efficiency,
since it produces spikes yet is a very simple model.
We also added
amplitude parameters to several neuron types,
Changing the amplitude of neural output
is useful for many
deep learning algorithms,
or when attempting to match a Nengo model
to a model implemented in another neural simulator.
We fixed several bugs related to pickling Nengo models, the decoder cache, and the config system.
To see the full list of changes in Nengo 2.7.0, head to the Github release page.
To get the new version of Nengo, use
pip install --upgrade nengo
Please come to the Nengo forum! We welcome any questions and suggestions you might have, and invite you to share your Nengo creations there.