The Nengo team is pleased to announce the release of Nengo 3.2.0!
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 3.2.0 is a minor release that is compatible with Python 3.6 - 3.9 (and likely Python 3.10 – please let us know if you run into any issues with Python 3.10).
The biggest change in this release is the addition of the
ConvolutionTranspose transform, which is useful for many types of convolutional neural networks.
We have removed support for Python 3.5 and NumPy versions before 1.19. If you cannot upgrade your Python or NumPy version, please use an earlier Nengo release. We also fixed 5 minor bugs and removed some unused and deprecated functions. To see the full list of changes, head to the Github release page.
To get the new version of Nengo, use
pip install --upgrade nengo
You’re already there! If you have an issue upgrading or have any other questions, please post them in this forum.