ABSTRACT
In this work, we apply a spiking neural network model and an associated memristive neuromorphic implementation to an application in classifying temporal scientific data. We demonstrate that the spiking neural network model achieves comparable results to a previously reported convolutional neural network model, with significantly fewer neurons and synapses required.
- S. Agostinelli et al. 2003. GEANT4: A Simulation toolkit. Nucl.Instrum.Meth. A506 (2003), 250--303.Google ScholarCross Ref
- Himanshu Akolkar, Cedric Meyer, Xavier Clady, Olivier Marre, Chiara Bartolozzi, Stefano Panzeri, and Ryad Benosman. 2015. What can neuromorphic event-driven precise timing add to spike-based pattern recognition? Neural computation (2015). Google ScholarDigital Library
- Filipp Akopyan, Jun Sawada, Andrew Cassidy, Rodrigo Alvarez-Icaza, John Arthur, Paul Merolla, Nabil Imam, Yutaka Nakamura, Pallab Datta, Gi-Joon Nam, et al. 2015. TrueNorth: Design and Tool Flow of a 65mW 1 Million Neuron Programmable Neurosynaptic Chip. (2015).Google Scholar
- L Aliaga, L Bagby, B Baldin, A Baumbaugh, A Bodek, R Bradford, WK Brooks, D Boehnlein, S Boyd, H Budd, et al. 2014. Design, calibration, and performance of the MINERvA detector. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 743 (2014), 130--159.Google ScholarCross Ref
- Costas Andreopoulos, A Bell, D Bhattacharya, F Cavanna, J Dobson, S Dytman, H Gallagher, P Guzowski, R Hatcher, P Kehayias, et al. 2010. The GENIE neutrino monte carlo generator. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 614, 1 (2010), 87--104.Google ScholarCross Ref
- Sander M Bohte, Joost N Kok, and Han La Poutre. 2002. Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48, 1 (2002), 17--37.Google ScholarCross Ref
- Yu Chen, Gang Liu, Cheng Wang, Wenbin Zhang, Run-Wei Li, and Luxing Wang. 2014. Polymer memristor for information storage and neuromorphic applications. Materials Horizons 1, 5 (2014), 489--506.Google ScholarCross Ref
- Mark E Dean and Christopher Daffron. 2016. A VLSI Design for Neuromorphic Computing. In VLSI (ISVLSI), 2016 IEEE Computer Society Annual Symposium on. IEEE, 87--92.Google ScholarCross Ref
- Bruce Denby, Patrick Garda, Bertrand Granado, Christian Kiesling, Jean-Christophe Prévotet, and Andreas Wassatsch. 2003. Fast triggering in high-energy physics experiments using hardware neural networks. Neural Networks, IEEE Transactions on 14, 5 (2003), 1010--1027. Google ScholarDigital Library
- Adam Disney, John Reynolds, Catherine D Schuman, Aleksander Klibisz, Aaron Young, and James S Plank. 2016. DANNA: A neuromorphic software ecosystem. Biologically Inspired Cognitive Architectures 17 (2016), 49--56.Google ScholarCross Ref
- Margaret Drouhard, Catherine D Schuman, J Douglas Birdwell, and Mark E Dean. 2014. Visual analytics for neuroscience-inspired dynamic architectures. In Foundations of Computational Intelligence (FOCI), 2014 IEEE Symposium on. IEEE, 106--113.Google ScholarCross Ref
- Victor Erokhin, Tatiana Berzina, Anteo Smerieri, Paolo Camorani, Svetlana Erokhina, and Marco P Fontana. 2010. Bio-inspired adaptive networks based on organic memristors. Nano Communication Networks 1, 2 (2010), 108--117.Google ScholarCross Ref
- Stefano Fusi. 2002. Hebbian spike-driven synaptic plasticity for learning patterns of mean firing rates. Biological cybernetics 87, 5 (2002), 459--470.Google Scholar
- Eugene M Izhikevich. 2003. Simple model of spiking neurons. IEEE Transactions on neural networks 14, 6 (2003), 1569--1572. Google ScholarDigital Library
- Sung Hyun Jo, Ting Chang, Idongesit Ebong, Bhavitavya B Bhadviya, Pinaki Mazumder, and Wei Lu. 2010. Nanoscale memristor device as synapse in neuromorphic systems. Nano letters 10, 4(2010), 1297--1301.Google Scholar
- Nikola Kasabov, Kshitij Dhoble, Nuttapod Nuntalid, and Giacomo Indiveri. 2013. Dynamic evolving spiking neural networks for on-line spatio-and spectro-temporal pattern recognition. Neural Networks 41 (2013), 188--201. Google ScholarDigital Library
- Dhireesha Kudithipudi, Qutaiba Saleh, Cory Merkel, James Thesing, and Bryant Wysocki. 2015. Design and Analysis of a Neuromemristive Reservoir Computing Architecture for Biosignal Processing. Frontiers in Neuroscience 9 (2015), 502.Google Scholar
- Bernabé Linares-Barranco and Teresa Serrano-Gotarredona. 2009. Memristance can explain spike-time-dependent-plasticity in neural synapses. (2009).Google Scholar
- Wolfgang Maass. 1997. Networks of spiking neurons: the third generation of neural network models. Neural networks 10, 9 (1997), 1659--1671. Google Scholar
- Liam P Maguire, T Martin McGinnity, Brendan Glackin, Arfan Ghani, Ammar Belatreche, and Jim Harkin. 2007. Challenges for large-scale implementations of spiking neural networks on FPGAs. Neurocomputing 71, 1 (2007), 13--29. Google ScholarDigital Library
- Garrick Orchard, Xavier Lagorce, Christoph Posch, Steve B Furber, Ryad Benosman, and Francesco Galluppi. 2015. Real-time event-driven spiking neural network object recognition on the SpiNNaker platform. In Circuits and Systems (ISCAS), 2015 IEEE International Symposium on. IEEE, 2413--2416.Google ScholarCross Ref
- NG Pavlidis, OK Tasoulis, Vassilis P Plagianakos, G Nikiforidis, and MN Vrahatis. 2005. Spiking neural network training using evolutionary algorithms. In Neural Networks, 2005. IJCNN'05. Proceedings. 2005 IEEE International Joint Conference on, Vol. 4. IEEE, 2190--2194.Google ScholarCross Ref
- J. S. Plank, G. S. Rose, M. E. Dean, and C. D. Schuman. 2017. A CAD System for Exploring Neuromorphic Computing with Emerging Technologies. In 42nd Annual GOMACTech Conference. Reno, NV.Google Scholar
- Anvesh Polepalli, Nicholas Soures, and Dhireesha Kudithipudi. 2016. Digital neuromorphic design of a Liquid State Machine for real-time processing. In Rebooting Computing (ICRC), IEEE International Conference on. IEEE, 1--8.Google Scholar
- Mirko Prezioso, Farnood Merrikh-Bayat, BD Hoskins, GC Adam, Konstantin K Likharev, and Dmitri B Strukov. 2015. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 7550 (2015), 61--64.Google Scholar
- Benjamin Schrauwen, Michiel DâĂŹHaene, David Verstraeten, and Jan Van Campenhout. 2008. Compact hardware liquid state machines on FPGA for real-time speech recognition. Neural networks 21, 2 (2008), 511--523. Google ScholarDigital Library
- Catherine D Schuman, J Douglas Birdwell, and Mark E Dean. 2014. Spatiotemporal classification using neuroscience-inspired dynamic architectures. Procedia Computer Science 41 (2014), 89--97.Google ScholarCross Ref
- Catherine D Schuman, Adam Disney, Susheela P Singh, Grant Bruer, J Parker Mitchell, Aleksander Klibisz, and James S Plank. 2016. Parallel evolutionary optimization for neuromorphic network training. In Proceedings of the Workshop on Machine Learning in High Performance Computing Environments. IEEE Press, 36--46. Google ScholarDigital Library
- Catherine D Schuman, James S Plank, Adam Disney, and John Reynolds. 2016. An evolutionary optimization framework for neural networks and neuromorphic architectures. In Neural Networks (IJCNN), 2016 International Joint Conference on. IEEE, 145--154.Google ScholarCross Ref
- Teresa Serrano-Gotarredona, Timothée Masquelier, Themistoklis Prodromakis, Giacomo Indiveri, and Bernabe Linares-Barranco. 2013. STDP and STDP variations with memristors for spiking neuromorphic learning systems. Frontiers in neuroscience 7 (2013), 2.Google Scholar
- Juncheng Shen, De Ma, Zonghua Gu, Ming Zhang, Xiaolei Zhu, Xiaoqiang Xu, Qi Xu, Yangjing Shen, and Gang Pan. 2016. Darwin: a neuromorphic hardware co-processor based on Spiking Neural Networks. Science China Information Sciences (2016), 1--5.Google Scholar
- Sen Song, Kenneth D Miller, and Larry F Abbott. 2000. Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature neuroscience 3, 9 (2000), 919--926.Google Scholar
- Adam M. Terwilliger, Gabriel N. Perdue, David Isele, Robert M. Patton, and Steven R. Young. 2017. Vertex Reconstruction of Neutrino Interactions using Deep Learning. In Neural Networks (IJCNN), 2017 International Joint Conference on. In Press.Google Scholar
- Andres Upegui, Carlos Andrés Pena-Reyes, and Eduardo Sanchez. 2005. An FPGA platform for on-line topology exploration of spiking neural networks. Microprocessors and microsystems 29, 5 (2005), 211--223.Google Scholar
- Salvatore Vitabile, Vincenzo Conti, Fulvio Gennaro, and Filippo Sorbello. 2005. Efficient MLP digital implementation on FPGA. In Digital System Design, 2005. Proceedings. 8th Euromicro Conference on. IEEE, 218--222. Google ScholarDigital Library
- Jianguo Xin and Mark J Embrechts. 2001. Supervised learning with spiking neural networks. In Neural Networks, 2001. Proceedings. IJCNN'01. International Joint Conference on, Vol. 3. IEEE, 1772--1777.Google Scholar
Index Terms
- Neuromorphic computing for temporal scientific data classification
Recommendations
Effects of Noise on Leaky Integrate-and-Fire Neuron Models for Neuromorphic Computing Applications
Computational Science and Its Applications – ICCSA 2022AbstractArtificial neural networks (ANNs) have been extensively used for the description of problems arising from biological systems and for constructing neuromorphic computing models. The third generation of ANNs, namely, spiking neural networks (SNNs), ...
Backpropagation for energy-efficient neuromorphic computing
NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1Solving real world problems with embedded neural networks requires both training algorithms that achieve high performance and compatible hardware that runs in real time while remaining energy efficient. For the former, deep learning using ...
Comments