Ivan Yu. Smolyakov
Lev A. Stankevich
Received 19 August 2021
The article proposes a new approach to the implementation of a neuromorphic system based on a hybrid model of a neuron, made in a neuro-fuzzy basis. The closest analogue, the Neo-fuzzy neuron model, is described. A neurological cluster model, previously developed with the participation of the authors, was chosen as a prototype for constructing a hybrid model. The basic procedures for processing and teaching this model to map a given function, as well as additional procedures for coding pulse inputs and synthesis of pulse outputs are presented. Using these procedures, a new hybrid model of a spike neuron has been implemented, which reflects the function of the traditional model of Izhikevich's neuron. It is shown that the hybrid model requires less computing resources. On the basis of the new version of the hybrid model, a spike neuromorphic network was developed and tested to control the movements of a mobile robot along a given trajectory. It is assumed that, using a hybrid version of the neuron model, it is easier to implement a hardware version of spike neuromorphic networks than using neuron models based on differential equations. On the basis of such hardware-implemented networks, it is possible to create effective neuromorphic control systems for mobile robots.
Neuromorphic system, spike neuromorphic network, hybrid neuron model, neuron-fuzzy basis, mobile robot control.
This work was done as the part of the state task of the Ministry of Education and Science of Russia No. 075-00913-21-01 «Development and study of new architectures of reconfigurable growing neural networks, methods and algorithms for their learning».
Smolyakov, I. and Stankevich, L., 2021. Hybrid implementation of neuromorphic system for robot control. Robotics and Technical Cybernetics, 9(4), pp.289-298.
- Maass, W., 1994. On the Computational Complexity of Networks of Spiking Neurons. In: Proceedings of NIPS'94, pp.183–190.
- Yu, Q. et al., 2016. A Spiking Neural Network System for Robust Sequence Recognition. IEEE Transactions on Neural Networks and Learning Systems, 27(3), pp.621–635. DOI: 10.1109/TNNLS.2015.2416771.
- Izhikevich, E.M., 2003. Simple model of spiking neurons. IEEE Transactions on Neural Networks, 14(6), pp.1569–1572. DOI: 10.1109/TNN.2003.820440.
- Bodyanskiy, Ye. and Kulishova, N., 2014. Extended neo-fuzzy neuron in the task of images filtering. Radio Electronics Computer Science Control, 1, pp.112–119. DOI: 10.15588/1607-3274-2014-1-16.
- Bodyanskiy, Ye. et al., 2020. Multilayer GMDH-neuro-fuzzy network based on extended neo-fuzzy neurons and its application in online facial expression recognition. System Research and Information Technologies, 3, pp.66–77. DOI: 10.20535/SRIT.2308-8893.2020.3.05.
- Stankevich, L.A., 2019. Kognitivnye Sistemy i Roboty: Monografiya [Cognitive Systems and Robots: Monograph]. Saint Petersburg: Politekh Press, p.631.
- Zadeh, L.A., 1975. The concept of a linguistic variable and its application to approximate reasoning. Information Sciences, 8(3), pp.199-249. DOI: 10.1016/0020-0255(75)90036-5.
- Bezanson J. et al., 2012. Julia: A Fast Dynamic Language for Technical Computing, arXiv:1209.5145v1 [cs.PL]. Available at: <https://arxiv.org/pdf/1209.5145.pdf> (Accessed 15 November 2021).
- Rackauckas, Ch. and Nie, Q., 2017. Differential Equations.jl – A Performant and Feature-Rich Ecosystem for Solving Differential Equations in Julia. Available at: <https://openresearchsoftware.metajnl.com/articles/5334/jors.151/> (Accessed 22 November 2021).
- Github.com, u.d. Evolutionary.jl. Available at: <https://wildart.github.io/Evolutionary.jl/stable/> (Accessed 22 November 2021).