The delay coincidence neural network (aka spikey neural networks) project deals with the identification of different dynamical regimes for spikey neural networks and exploitation of these regimes in neural network applications involving reactive and planning components.

Spikey Neural Networks Publications

    [1]
    A. Bennett and T. White, “Dynamical properties of spiking neural networks with small world topologies,” Proceedings of the 21st ACM International Conference on Intelligent Virtual Agents, Sep. 2021.
    [2]
    F. Jeanson and T. White, “Decoding Coincidence Detection Thresholds for Dynamic Memory,” in Proceedings of the 12th International Conference on Cognitive Modelling (ICCM ’13), Ottawa, Canada, 2013.
    [3]
    F. Jeanson and T. White, “Evolving axonal delay neural networks for robot control,” in Proceedings of the fourteenth international conference on Genetic and Evolutionary Computation Conference, 2012, pp. 121–128.
    [4]
    A. Bennett and T. White, “Synfire Circuits: Constraint Programming Technique for Combining Functional Groupings of Spiking Neurons,” Biologically Inspired Cognitive Architectures, Jul. 2018.
    [5]
    F. Jeanson and T. White, “Dynamic Memory for Robot Control via Delay Neural Networks,” in 23rd International Conference on Artificial Neural Networks (ICANN ’13), Sofia, Bulgaria, 2013.
    [6]
    F. Jeanson and T. White, “Dynamic Memory via Delay Coincidence Detection for Robot Maze Navigation,” in Proceedings of the 22nd International Conference on Genetic and Evolutionary Computation (GECCO ’13), Amsterdam, The Netherlands, 2013.