The Nengo team is pumped to announce the release of Nengo 2.5.0!
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 2.5.0 contains several improvements to documentation, bugfixes, and a few new features.
Networks now have an
that gives the number of neurons in the network,
including all subnetworks.
It is now possible to combine
to implement more complex synapses types like double exponentials.
Neuron types can now determine maximum firing rates
and intercepts given gain and bias values.
If the gain and bias is specified,
the maximum firing rates and intercepts will be
determined in the build process,
or can be found at any time using the
To see the full list of changes in Nengo 2.5.0, 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.