The Nengo DL team is excited to announce the release of Nengo DL 0.5.2.
Nengo DL is a backend for Nengo that integrates deep learning methods (supported by the TensorFlow framework) with other Nengo modelling tools. This allows users to optimize their models using deep learning training methods, improves simulation speed (on CPU or GPU), and makes it easy to insert TensorFlow models (such as a convolutional neural network) into Nengo networks.
To use Nengo DL, replace instances of
For example, if you have a network called
model and you run it with
with nengo.Simulator(model) as sim: sim.run(10)
you would change that to
with nengo_dl.Simulator(model) as sim: sim.run(10)
and that’s it!
Information on accessing the more advanced features of Nengo DL can be found in the documentation.
0.5.2 contains a number of usability improvement that make it easier to optimize Nengo models, such as support for visualizing data in TensorBoard, variable learning rate schedules, and multi-objective training. We’ve also added two new examples that demonstrate how NengoDL can be used to improve performance in more complicated SPA models (thanks to new contributor @pblouw). And, as always, we’ve fixed some bugs. Check out the GitHub release page for a full changelog.
To install Nengo DL, we recommend using
pip install nengo_dl
More detailed installation instructions can be found here.
Please come to the Nengo forum! We welcome any questions and suggestions you might have.