Three Tools for the Real-Time Simulation of Embodied Spiking Neural Networks Using GPUs
- 1.3k Downloads
This paper presents a toolbox of solutions that enable the user to construct biologically-inspired spiking neural networks with tens of thousands of neurons and millions of connections that can be simulated in real time, visualized in 3D and connected to robots and other devices. NeMo is a high performance simulator that works with a variety of neural and oscillator models and performs parallel simulations on either GPUs or multi-core processors. SpikeStream is a visualization and analysis environment that works with NeMo and can construct networks, store them in a database and visualize their activity in 3D. The iSpike library provides biologically-inspired conversion between real data and spike representations to support work with robots, such as the iCub. Each of the tools described in this paper can be used independently with other software, and they also work well together.
KeywordsSimulation 3D visualization Spike encoding Robotics Spiking neural networks iCub GPU
This work was supported by EPSRC grant EP/F033516/1. Some of the GPUs used were funded through the NVIDIA University Program. We would also like to thank the reviewers of this paper for their helpful comments.
- Aleksander, I. (2005). The world in my mind, my mind in the world. Exeter: Imprint Academic.Google Scholar
- Andreou, A., & Boahen, K. (1994). A 48,000 pixel silicon retina in current-mode subthreshold cmos. In 37th midwest symposium on circuits and systems (pp. 97–102).Google Scholar
- Bernhard, F., & Keriven, R. (2006). Spiking neurons on GPUs. In Proc. 6th int. conf. computational science (pp. 236–243).Google Scholar
- Bhowmik, D., & Shanahan, M. (2012). How well do oscillator models capture the behaviour of biological neurons? In Proc. int. joint conf. neural networks.Google Scholar
- Bouganis, A., & Shanahan, M. (2010). Training a spiking neural network to control a 4-DoF robotic arm based on spike timing-dependent plasticity. In Proc. int. joint conf. neural networks (pp. 4104–4111).Google Scholar
- Bower, J.M., Beeman, D., Hucka, M. (2003). The GENESIS simulation system In M. Arbib (Ed.), In The handbook of brain theory and neural networks (2nd ed., 475–478). Cambridge: MIT Press.Google Scholar
- Brette, R., Rudolph, M., Carnevale, T., Hines, M., Beeman, D., Bower, J.M., Diesmann, M.,Morrison, A., Goodman, P.H., Harris, F.C. Jr., Zirpe, M., Natschlager, T., Pecevski, D., Ermentrout, B., Djurfeldt, M., Lansner, A., Rochel, O., Vieville, T., Muller, E., Davison, A.P., El Boustani, S., Destexhe, A. (2007). Simulation of networks of spiking neurons: a review of tools and strategies. Journal of Computational Neuroscience, 23(3), 349–398.PubMedCrossRefGoogle Scholar
- Buchmann, T. (2011). Stock market trading with spiking neural networks. MSc thesis, Imperial College London.Google Scholar
- Cannata, G., Maggiali, M., Metta, G., Sandini, G. (2008). An embedded artificial skin for humanoid robots. In IEEE int. conf. multisensor fusion and integration for intelligent systems (pp. 434–438).Google Scholar
- Cheung, K., Schultz, S.R., Leong, P.H.W. (2009). A parallel spiking neural network simulator. In Proc. IEEE. int. conf. field-programmable technology (pp. 247–254).Google Scholar
- Clark, A. (2008). Supersizing the mind: Embodiment, action, and cognitive extension. New York: Oxford University Press.Google Scholar
- Davison, A.P., Brüderle, D., Eppler, J., Kremkow, J., Muller, E., Pecevski, D., Perrinet, L., Yger, P. (2008). PyNN: a common interface for neuronal network simulators. Frontiers in Neuroinformatics, 2, article 11.Google Scholar
- Fidjeland, A.K. (2011). NeMo manual. http://nemosim.sf.net/manual.pdf.
- Fidjeland, A.K., Roesch, E.B., Shanahan, M.P., Luk, W. (2009). NeMo: a platform for neural modelling of spiking neurons using GPUs. In Proc. IEEE int. conf application-specific systems, architectures and processors (pp. 137–144).Google Scholar
- Fidjeland, A., & Shanahan, M. (2010). Accelerated simulation of spiking neural networks using GPUs. In Proc. int. joint conf. neural networks (pp. 536–543). Piscataway: IEEE.Google Scholar
- Fountas, Z., Gamez, D., Fidjeland, A. (2011). A neuronal global workspace for human-like control of a computer game character. In IEEE conf. computational intelligence and games (pp. 350–357).Google Scholar
- Gamez, D. (2007). Spikestream: a fast and flexible simulator of spiking neural networks. In Proceedings of the International Conference on Artificial Neural Networks (ICANN). Lecture Notes in Computer Science (Vol. 4668, pp. 360–369).Google Scholar
- Gamez, D. (2011a). iSpike manual. http://ispike.sf.net/doc/ispike-manual-2.1.pdf.
- Gamez, D. (2011b). SpikeStream manual. http://spikestream.sf.net/pages/documentation.html.
- Gamez, D., Newcombe, R., Holland, O., Knight, R. (2006). Two simulation tools for biologically inspired virtual robotics. In Proc. IEEE 5th chapter conf. on advances in cybernetic systems (pp. 85–90).Google Scholar
- Han, B., & Taha, T.M. (2010). Neuromorphic models on a GPGPU cluster. In Proc int. joint conf. neural networks (pp. 3050–3057). Piscataway: IEEE.Google Scholar
- Hoshi, T., & Shinoda, H. (2006). Robot skin based on touch-area-sensitive tactile element. In Proc. IEEE int. conf. robotics and automation (pp. 3463–3468).Google Scholar
- Indiveri, G., Linares-Barranco, B., Hamilton, T.J., van Schaik, A., Etienne-Cummings, R., Delbruck, T., Liu, S.C., Dudek, P., Hafliger, P., Renaud, S., Schemmel, J., Cauwenberghs, G., Arthur, J., Hynna, K., Folowosele, F., Saighi, S., Serrano-Gotarredona, T., Wijekoon, J., Wang, Y., Boahen, K. (2011). Neuromorphic silicon neuron circuits. Frontiers Neuroscience, 5, 73.Google Scholar
- Linares-Barranco, A., Gomez-Rodriguez, F., Jimenez-Fernandez, A., Delbruck, T., Lichtensteiner, P. (2007). Using FPGA for visuomotor control with a silicon retina and a humanoid robot. In IEEE int. symp. circuits and systems (pp. 1192–1195).Google Scholar
- Lyon, R. (1982). A computational model of filtering, detection, and compression in the cochlea. IEEE International Conference on Acoustics, Speech, and Signal Processing, 7, 1282–1285.Google Scholar
- Marques, H., Jäntsch, M., Wittmeier, S., Alessandro, C., Holland, O., Diamond, A., Lungarella, M., Knight, R. (2010). ECCE1: the first of a series of anthropomimetic musculoskelal upper torsos. In Proc. IEEE int. conf. humanoid robotics (pp. 391–396).Google Scholar
- Metta, G., Sandini, G., Vernon, D., Natale, L., Nori, F. (2008). The iCub humanoid robot: an open platform for research in embodied cognition. In Proc. workshop on performance metrics for intelligent systems.Google Scholar
- Noë, A., & Thompson, E. (2004). Are there neural correlates of consciousness? Journal of Consciousness Studies, 11(1), 3–28.Google Scholar
- Ribot-Ciscar, E., Bergenheim, M., Albert, F., Roll, J.P. (2003). Proprioceptive population coding of limb position in humans. Experimental Brain Research, 149(4), 512–519.Google Scholar
- Schemmel, J., Brüderle, D., Grübl, A., Hock, M., Meier, K., Millner, S. (2010). A wafer-scale neuromorphic hardware system for large-scale neural modeling. In Proc. IEEE int. conf. circuits and systems (pp. 1947–1950).Google Scholar
- Thomas, D.B., & Luk, W. (2009). FPGA accelerated simulation of biologically plausible spiking neural networks. In Proc. IEEE symp. field-programmable custom computing machines.Google Scholar
- Tiesel, J.P., & Maida, A.S. (2009). Using parallel GPU architecture for simulation of planar I/F networks. In Proc int. joint conf. neural networks (pp. 754–759). 1602Google Scholar
- Yudanov, D., Shaaban, M., Melton, R., Reznik, L. (2010). GPU-based simulation of spiking neural networks with real-time performance and high accuracy. In Proc. int. joint conf. neural networks.Google Scholar