Success stories

Nengolib has been used successfully for several peer-reviewed publications and self-published projects. We highlight these applications below:

  • Aaron R. Voelker and Chris Eliasmith, “Improving spiking dynamical networks: Accurate delays, higher-order synapses, and time cells”, Neural Computation, 30(3):569-609, 03 2018.

    [PDF] [Code] Used RollingWindow, PadeDelay(), and ss2sim() to model time cell activity in rodents and improve the accuracy of dynamical systems in spiking neural networks.

  • Aaron R. Voelker and Chris Eliasmith, “Methods for applying the Neural Engineering Framework to neuromorphic hardware”, arXiv preprint arXiv:1708.08133, 08 2017.

    [Paper] Provides a theoretical overview of the math leveraged by ss2sim() and its related extensions.

  • Travis DeWolf. “Improving neural models by compensating for discrete rather than continuous filter dynamics when simulating on digital systems”, 05 2017.

    [Blog] Used ss2sim() to improve the accuracy of a point attractor.

  • Aaron R. Voelker, Ben V. Benjamin, Terrence C. Stewart, Kwabena Boahen, and Chris Eliasmith. “Extending the Neural Engineering Framework for nonideal silicon synapses”, In IEEE International Symposium on Circuits and Systems (ISCAS). Baltimore, MD, 05 2017. IEEE.

    [PDF] [Poster] Used HeteroSynapse, s, z, ball, sphere, and the theory behind ss2sim() to improve the accuracy of nonlinear dynamics on a mixed-analog-digital neuromorphic architecture.

  • James Knight, Aaron R. Voelker, Andrew Mundy, Chris Eliasmith, and Steve Furber. “Efficient spinnaker simulation of a heteroassociative memory using the Neural Engineering Framework”. In The 2016 International Joint Conference on Neural Networks (IJCNN). Vancouver, British Columbia, 07 2016. IEEE.

    [Paper] Used leech_kissing() and sphere to learn an efficient heteroassociative memory on SpiNNaker.

  • Ken E. Friedl, Aaron R. Voelker, Angelika Peer, and Chris Eliasmith. “Human-inspired neurorobotic system for classifying surface textures by touch”, Robotics and Automation Letters, 1(1):516-523, 01 2016. URL: http://dx.doi.org/10.1109/LRA.2016.2517213, doi:10.1109/LRA.2016.2517213.

    [PDF] Used HeteroSynapse, Bandpass(), and Highpass() to engineer a biologically inspired approach to online tactile classification of surface textures.