STDP-based Unsupervised Feature Learning using Convolution-over-time in Spiking Neural Networks for Energy-Efficient Neuromorphic Computing

Abstract

Brain-inspired learning models attempt to mimic the computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we propose Spike Timing Dependent Plasticity-based unsupervised feature learning using convolution-over-time in Spiking Neural Network (SNN). We use shared weight kernels that are convolved with the input patterns over time to encode representative input features, thereby improving the sparsity as well as the robustness of the learning model. We show that the Convolutional SNN self-learns several visual categories for object recognition with limited number of training patterns while yielding comparable classification accuracy relative to the fully connected SNN. Further, we quantify the energy benefits of the Convolutional SNN over fully connected SNN on neuromorphic hardware implementation.

References

1. Guo-qiang Bi and Mu-ming Poo. 1998. Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type. J. Neurosci. 18, 24 (1998), 10464--10472.
2. Gary Bradski. 2000. The opencv library. Dr. Dobb’s J. Softw. Tools Prof. Programmer 25, 11 (2000), 120--123.
3. Indranil Chakraborty, Deboleena Roy, and Kaushik Roy. 2017. Technology aware training in memristive neuromorphic systems based on non-ideal synaptic crossbars. arXiv Preprint arXiv:1711.08889.
4. Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Choday, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain et al. 2018. Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 1 (2018), 82--99.
5. Peter U. Diehl and Matthew Cook. 2015. Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 9 (2015), 99.
6. Li Fei-Fei, Rob Fergus, and Pietro Perona. 2007. Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput. Vision Image Understand. 106, 1 (2007), 59--70.
7. Paul Ferré, Franck Mamalet, and Simon J. Thorpe. 2018. Unsupervised feature learning with winner-takes-all based STDP. Front. Comput. Neurosci. 12 (2018), 24.
8. Dan Goodman and Romain Brette. 2008. Brian: A simulator for spiking neural networks in Python. Front. Neuroinfo. 2 (2008), 5.
9. Akhilesh Jaiswal, Sourjya Roy, Gopalakrishnan Srinivasan, and Kaushik Roy. 2017. Proposal for a leaky-integrate-fire spiking neuron based on magnetoelectric switching of ferromagnets. IEEE Trans. Electron. Dev. 64, 4 (2017), 1818--1824.
10. Yingyezhe Jin, Peng Li, and Wenrui Zhang. 2018. Hybrid macro/micro level backpropagation for training deep spiking neural networks. arXiv Preprint arXiv:1805.07866v1.
11. 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 Lett. 10, 4 (2010), 1297--1301.
12. Florian Jug. 2012. On Competition and Learning in Cortical Structures. Ph.D. Dissertation. ETH Zurich.
13. Muhammad Mukaram Khan, David R. Lester, Luis A. Plana, A. Rast, Xin Jin, Eustace Painkras, and Stephen B. Furber. 2008. SpiNNaker: Mapping neural networks onto a massively parallel chip multiprocessor. In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN’08). Ieee, Hong Kong, China, 2849--2856.
14. Saeed Reza Kheradpisheh, Mohammad Ganjtabesh, Simon J. Thorpe, and Timothe Masquelier. 2018. STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99 (2018), 56--67.
15. Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.
16. Chankyu Lee, Priyadarshini Panda, Gopalakrishnan Srinivasan, and Kaushik Roy. 2018. Training deep spiking convolutional neural networks with stdp-based unsupervised pre-training followed by supervised fine-tuning. Front. Neurosci. 12 (2018), 435.
17. Chankyu Lee, Gopalakrishnan Srinivasan, Priyadarshini Panda, and Kaushik Roy. 2018. Deep spiking convolutional neural network trained with unsupervised spike timing dependent plasticity. IEEE Trans. Cogn. Dev. Syst. (2018), 1--1.
18. Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. 2016. Training deep spiking neural networks using backpropagation. Front. Neurosci. 10 (2016), 508.
19. Timothée Masquelier and Simon J. Thorpe. 2007. Unsupervised learning of visual features through spike timing dependent plasticity. PLoS Comput. Biol. 3, 2 (2007), e31.
20. Paul A. Merolla, John V. Arthur, Rodrigo Alvarez-Icaza, Andrew S. Cassidy, Jun Sawada, Filipp Akopyan, Bryan L. Jackson, Nabil Imam, Chen Guo, Yutaka Nakamura et al. 2014. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 6197 (2014), 668--673.
21. Priyadarshini Panda and Kaushik Roy. 2016. Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition. In Proceedings of the International Joint Conference on Neural Networks (IJCNN’16). IEEE, Vancouver, British Columbia, Canada, 299--306.
22. Nitin Rathi, Priyadarshini Panda, and Kaushik Roy. 2018. STDP based pruning of connections and weight quantization in spiking neural networks for energy-efficient recognition. IEEE Trans. Comput.-Aided Des. Integr. Circ. Syst. (2018), 1--1.
23. Abhronil Sengupta, Zubair Al Azim, Xuanyao Fong, and Kaushik Roy. 2015. Spin-orbit torque induced spike-timing dependent plasticity. Appl. Phys. Lett. 106, 9 (2015), 093704.
24. Abhronil Sengupta, Aparajita Banerjee, and Kaushik Roy. 2016. Hybrid spintronic-CMOS spiking neural network with on-chip learning: Devices, circuits, and systems. Phys. Rev. Appl. 6, 6 (2016), 064003.
25. Abhronil Sengupta, Priyadarshini Panda, Parami Wijesinghe, Yusung Kim, and Kaushik Roy. 2016. Magnetic tunnel junction mimics stochastic cortical spiking neurons. Sci. Rep. 6 (2016), 30039.
26. Manan Suri, Olivier Bichler, Damien Querlioz, Olga Cueto, Luca Perniola, Veronique Sousa, Dominique Vuillaume, Christian Gamrat, and Barbara DeSalvo. 2011. Phase change memory as synapse for ultra-dense neuromorphic systems: Application to complex visual pattern extraction. In Proceedings of the IEEE International Electron Devices Meeting (IEDM’11). IEEE, Washington, DC, 4--4.
27. Amirhossein Tavanaei, Timothée Masquelier, and Anthony S. Maida. 2016. Acquisition of visual features through probabilistic spike-timing-dependent plasticity. In Proceedings of the International Joint Conference on Neural Networks (IJCNN’16). IEEE, Vancouver, British Columbia, Canada, 307--314.
28. Johannes C. Thiele, Olivier Bichler, and Antoine Dupret. 2018. Event-based, timescale invariant unsupervised online deep learning with STDP. Front. Comput. Neurosci. 12 (2018), 46.
29. Tomas Tuma, Angeliki Pantazi, Manuel Le Gallo, Abu Sebastian, and Evangelos Eleftheriou. 2016. Stochastic phase-change neurons. Nature Nanotechnol. 11, 8 (2016), 693--699.
30. Yujie Wu, Lei Deng, Guoqi Li, Jun Zhu, and Luping Shi. 2018. Spatio-temporal backpropagation for training high-performance spiking neural networks. Front. Neurosci. 12 (2018), 331.

Index Terms

• Computing methodologies

  • Machine learning

    • Machine learning approaches

      • Neural networks

• Hardware

  • Emerging technologies

    • Spintronics and magnetic technologies