ABSTRACT
Neuromorphic computing systems simulate spiking neural networks that are used for research into how biological neural networks function, as well as for applied engineering such as robotics, pattern recognition, and machine learning. In this paper, we present a neuromorphic system based on an asynchronous event-based hardware platform. We represent three algorithms for implementing spiking networks on our asynchronous hardware platform. We also discuss different trade-offs between synchronisation and messaging costs. A reinforcement learning method known as Reward-modulated STDP is presented as an online learning algorithm in the network. We evaluate the system performance in a single box of our designed architecture using 6000 concurrent hardware threads and demonstrate scaling to networks with up to 2 million neurons and 400 million synapses. The performance of our architecture is also compared to existing neuromorphic platforms, showing a 20 times speed-up over the Brian simulator on an x86 machine, and a 16 times speed-up over a 48-chip SpiNNaker node.
- B. V. Benjamin and et. al. 2014. Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations. Proc. IEEE 102, 5 (May 2014), 699–716. https://doi.org/10.1109/JPROC.2014.2313565Google Scholar
- Romain Brette and et. al. 2007. Simulation of networks of spiking neurons: A review of tools and strategies. 23, 3 (2007), 349–398, 2007. https://doi.org/10.1007/s10827-007-0038-6Google Scholar
- Kit Cheung, Simon R. Schultz, and Wayne Luk. 2012. A Large-Scale Spiking Neural Network Accelerator for FPGA Systems. In ICANN. Springer, 113–120.Google Scholar
- Kit Cheung, Simon R. Schultz, and Wayne Luk. 2016. NeuroFlow: A General Purpose Spiking Neural Network Simulation Platform using Customizable Processors. Frontiers in Neuroscience 9 (2016), 516. https://doi.org/10.3389/fnins.2015.00516Google ScholarCross Ref
- Mike Davies and et al.2018. Loihi: A Neuromorphic Manycore Processor with On-Chip Learning. 38, 1 (2018), 82–99. https://doi.org/10.1109/MM.2018.112130359 IEEE Micro, 2018.Google Scholar
- Mazdak Fatahi, Mahyar Shahsavari, Mahmood Ahmadi, Arash Ahmadi, Pierre Boulet, and Philippe Devienne. 2018. Rate-coded DBN: An online strategy for spike-based deep belief networks. Biologically Inspired Cognitive Architectures 24 (April 2018), 59–69. https://doi.org/10.1016/j.bica.2018.04.009Google Scholar
- S. B. Furber, F. Galluppi, S. Temple, and L. A. Plana. 2014. The SpiNNaker Project. Proc. IEEE 102, 5 (2014), 652–665. https://doi.org/10.1109/JPROC.2014.2304638Google ScholarCross Ref
- E. M. Izhikevich. 2003. Simple Model of Spiking Neurons. Trans. Neur. Netw. 14, 6 (Nov. 2003), 1569–1572. https://doi.org/10.1109/TNN.2003.820440Google ScholarDigital Library
- Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. 2016. Training Deep Spiking Neural Networks Using Backpropagation. Frontiers in Neuroscience 10 (2016). https://doi.org/10.3389/fnins.2016.00508 Publisher: Frontiers.Google Scholar
- Robert Legenstein, Dejan Pecevski, and Wolfgang Maass. 2008. A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback. PLOS Computational Biology 4, 10 (10 2008), 1–27. https://doi.org/10.1371/journal.pcbi.1000180Google Scholar
- De Ma, Juncheng Shen, Zonghua Gu, Ming Zhang, Xiaolei Zhu, Xiaoqiang Xu, Qi Xu, Yangjing Shen, and Gang Pan. 2017. Darwin: A neuromorphic hardware co-processor based on spiking neural networks. 77 (2017), 43 – 51, 2017. https://doi.org/10.1016/j.sysarc.2017.01.003Google Scholar
- Paul A. Merolla and et al.2014. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 6197 (Aug. 2014), 668–673. https://doi.org/10.1126/science.1254642Google ScholarCross Ref
- Milad Mozafari, Saeed Reza Kheradpisheh, Timothée Masquelier, Abbas Nowzari-Dalini, and Mohammad Ganjtabesh. 2018. First-Spike-Based Visual Categorization Using Reward-Modulated STDP. IEEE Transactions on Neural Networks and Learning Systems 29, 12(2018), 6178–6190. https://doi.org/10.1109/TNNLS.2018.2826721Google ScholarCross Ref
- M. Naylor, S. W. Moore, and D. Thomas. 2019. Tinsel: A Manythread Overlay for FPGA Clusters. In 29th FPL. 375–383. https://doi.org/10.1109/FPL.2019.00066Google Scholar
- Michael Pfeiffer and Thomas Pfeil. 2018. Deep Learning With Spiking Neurons: Opportunities and Challenges. Frontiers Neurosci 12(2018), 774. https://doi.org/10.3389/fnins.2018.00774Google ScholarCross Ref
- Alexander Rast, Mahyar Shahsavari, Graeme M. Bragg, Mark L. Vousden, David Thomas, and Andrew Brown. 2020. A Hardware/Application Overlay Model for Large-Scale Neuromorphic Simulation. In 2020 International Joint Conference on Neural Networks (IJCNN). 1–9. https://doi.org/10.1109/IJCNN48605.2020.9206708Google ScholarCross Ref
- Johannes Schemmel, Daniel Briiderle, Andreas Griibl, Matthias Hock, Karlheinz Meier, and Sebastian Millner. 2010. A wafer-scale neuromorphic hardware system for large-scale neural modeling. IEEE, 1947–1950. https://doi.org/10.1109/ISCAS.2010.5536970Google Scholar
- Mahyar Shahsavari, Jonathan Beaumont, David Thomas, and Andrew Brown. 2021. POETS: A Parallel Cluster Architecture for Spiking Neural Network. IJMLC 11, 4 (2021), 281–285. https://doi.org/10.18178/ijmlc.2021.11.4.1048Google ScholarCross Ref
- Mahyar Shahsavari and Pierre Boulet. 2018. Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures. IEEE Transactions on Multi-Scale Computing Systems 4, 4 (2018), 833–846. https://doi.org/10.1109/TMSCS.2017.2761231Google ScholarCross Ref
- M. Shahsavari, P. Devienne, and P. Boulet. 2015. N2S3, a Simulator for the Architecture Exploration of Neuromorphic Accelerators. In 2nd International Workshop on Neuromorphic and Brain-Based Computing Systems (NeuComp 2015) in DATE Conference, Grenoble, France.Google Scholar
- Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement Learning: An Introduction. MIT Press. http://www.cs.ualberta.ca/~sutton/book/the-book.htmlGoogle ScholarDigital Library
- Amirhossein Tavanaei, Masoud Ghodrati, Saeed Reza Kheradpisheh, Timothée Masquelier, and Anthony Maida. 2019. Deep learning in spiking neural networks. Neural Networks 111(2019), 47 – 63. https://doi.org/10.1016/j.neunet.2018.12.002Google ScholarDigital Library
- M. Walravens, E. Verreyken, and J. Steckel. 2020. Spiking Neural Network Implementation on FPGA for Robotic Behaviour. Lecture Notes in Networks and Systems 96 (2020), 694–703. https://doi.org/10.1007/978-3-030-33509-0_65Google ScholarCross Ref
- Timo Wunderlich, Akos F. Kungl, Eric Müller, Andreas Hartel, Yannik Stradmann, Syed Ahmed Aamir, Andreas Grübl, Arthur Heimbrecht, Korbinian Schreiber, David Stöckel, Christian Pehle, Sebastian Billaudelle, Gerd Kiene, Christian Mauch, Johannes Schemmel, Karlheinz Meier, and Mihai A. Petrovici. 2019. Demonstrating Advantages of Neuromorphic Computation: A Pilot Study. Frontiers in Neuroscience 13 (March 2019). https://doi.org/10.3389/fnins.2019.00260Google Scholar
- Shijie Zhou, Rajgopal Kannan, Hanqing Zeng, and Viktor K. Prasanna. 2018. An FPGA Framework for Edge-Centric Graph Processing. In Proceedings of the 15th ACM ICCF(Ischia, Italy). NY, USA, 69–77. https://doi.org/10.1145/3203217.3203233Google ScholarDigital Library
- Neuromorphic Design Using Reward-based STDP Learning on Event-Based Reconfigurable Cluster Architecture
Recommendations
Hardware design of LIF with Latency neuron model with memristive STDP synapses
In this paper, the hardware implementation of a neuromorphic system is presented. This system is composed of a Leaky Integrate-and-Fire with Latency (LIFL) neuron and a Spike-Timing Dependent Plasticity (STDP) synapse. LIFL neuron model allows to encode ...
Bio-plausible digital implementation of a reward modulated STDP synapse
AbstractReward-modulated Spike-Timing-Dependent Plasticity (R-STDP) is a learning method for Spiking Neural Network (SNN) that makes use of an external learning signal to modulate the synaptic plasticity produced by Spike-Timing-Dependent Plasticity (STDP)...
Simulating a complete Tritonia escape swim network using a novel event-based spiking neural network algorithm
AbstractTritonia has been studied in the laboratory by several studies, which have led to significant advances in identifying the biological components that participate in the Tritonia escape swim network. There are also studies, which have artificially ...
Comments