nengolib 0.5.1

Tools for robust dynamics in Nengo

import nengolib

Additional extensions and tools for modelling dynamical systems in Nengo.

Documentation

This project’s documentation is hosted on GitHub.IO: https://arvoelke.github.io/nengolib-docs/.

Development

To install the development version of nengolib:

git clone https://github.com/arvoelke/nengolib
cd nengolib
python setup.py develop

Notebooks can be run manually in docs/notebooks by running:

pip install jupyter
jupyter notebook

Release History

0.5.1 (April 17, 2019)

Tested against Nengo versions 2.2.0-2.8.0. Requires nengo<3.0.

Fixed

• A variety of miscellaneous fixes were made to the documentation. The nengolib.networks.RollingWindow documentation references the shifted Legendre polynomial equations for legendre == True. (#176)

0.5.0 (March 9, 2019)

Tested against Nengo versions 2.2.0-2.8.0. We now require numpy>=1.13.0, scipy>=0.19.0, and nengo>=2.2.0.

Added

• Added the nengolib.RLS() recursive least-squares (RLS) learning rule. This can be substituted for nengo.PES(). See notebooks/examples/full_force_learning.ipynb for an example that uses this to implement spiking FORCE in Nengo. (#133)

• Added the nengolib.stats.Rd() method for quasi-random sampling of arbitrarily high-dimensional vectors. It is now the default method for scattered sampling of encoders and evaluation points. The method can be manually switched back to nengolib.stats.Sobol(). (#153)

• Added the nengolib.neuron.init_lif(sim, ens) helper function for initializing the neural state of a LIF ensemble, from within a simulator block, to represent 0 uniformly at the start. (#156)

• Added nengolib.synapses.LegendreDelay as an alternative to nengolib.synapses.PadeDelay – it has an equivalent transfer function but a state-space realization corresponding to the shifted Legendre basis. The network nengolib.networks.RollingWindow support legendre=True to make this system the default realization. (#161)

Fixed

• Release no longer requires pytest. (#156)

0.4.2 (May 18, 2018)

Tested against Nengo versions 2.1.0-2.7.0.

Added

• Solving for connection weights by accounting for the neural dynamics. To use, pass in nengolib.Temporal() to nengo.Connection for the solver parameter. Requires nengo>=2.5.0. (#137)

0.4.1 (December 5, 2017)

Tested against Nengo versions 2.1.0-2.6.0.

Fixed

• Compatible with newest SciPy release (1.0.0). (#130)

0.4.0b (June 7, 2017)

Initial beta release of nengolib. Tested against Nengo versions 2.1.0-2.4.0.