Papers
Topics
Authors
Recent
Search
2000 character limit reached

Spatial-Temporal Search for Spiking Neural Networks

Published 24 Oct 2024 in cs.NE | (2410.18580v1)

Abstract: Spiking Neural Networks (SNNs) are considered as a potential candidate for the next generation of artificial intelligence with appealing characteristics such as sparse computation and inherent temporal dynamics. By adopting architectures of Artificial Neural Networks (ANNs), SNNs achieve competitive performances on benchmark tasks like image classification. However, successful architectures of ANNs are not optimal for SNNs. In this work, we apply Neural Architecture Search (NAS) to find suitable architectures for SNNs. Previous NAS methods for SNNs focus primarily on the spatial dimension, with a notable lack of consideration for the temporal dynamics that are of critical importance for SNNs. Drawing inspiration from the heterogeneity of biological neural networks, we propose a differentiable approach to optimize SNN on both spatial and temporal dimensions. At spatial level, we have developed a spike-based differentiable hierarchical search (SpikeDHS) framework, where spike-based operation is optimized on both the cell and the layer level under computational constraints. We further propose a differentiable surrogate gradient search (DGS) method to evolve local SG functions independently during training. At temporal level, we explore an optimal configuration of diverse temporal dynamics on different types of spiking neurons by evolving their time constants, based on which we further develop hybrid networks combining SNN and ANN, balancing both accuracy and efficiency. Our methods achieve comparable classification performance of CIFAR10/100 and ImageNet with accuracies of 96.43%, 78.96%, and 70.21%, respectively. On event-based deep stereo, our methods find optimal layer variation and surpass the accuracy of specially designed ANNs with 26$\times$ lower computational cost ($6.7\mathrm{mJ}$), demonstrating the potential of SNN in processing highly sparse and dynamic signals.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (99)
  1. W. Maass, “Networks of spiking neurons: the third generation of neural network models,” Neural Networks, vol. 10, no. 9, pp. 1659–1671, 1997.
  2. S. M. Bohte, J. N. Kok, and J. A. La Poutré, “Spikeprop: backpropagation for networks of spiking neurons.” in European Symposium on Artificial Neural Networks (ESANN), vol. 48.   Bruges, 2000, pp. 419–424.
  3. Y. Wu, L. Deng, G. Li, J. Zhu, and L. Shi, “Spatio-temporal backpropagation for training high-performance spiking neural networks,” Frontiers in Neuroscience, vol. 12, p. 331, 2018.
  4. E. O. Neftci, H. Mostafa, and F. Zenke, “Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks,” IEEE Signal Processing Magazine, vol. 36, no. 6, pp. 51–63, 2019.
  5. S. B. Shrestha and G. Orchard, “Slayer: Spike layer error reassignment in time,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 31, 2018.
  6. Y. Wu, L. Deng, G. Li, J. Zhu, Y. Xie, and L. Shi, “Direct training for spiking neural networks: Faster, larger, better,” in Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), vol. 33, no. 01, 2019, pp. 1311–1318.
  7. W. Zhang and P. Li, “Temporal spike sequence learning via backpropagation for deep spiking neural networks,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 12 022–12 033, 2020.
  8. N. Rathi and K. Roy, “Diet-snn: A low-latency spiking neural network with direct input encoding and leakage and threshold optimization,” IEEE Transactions on Neural Networks and Learning Systems, 2021.
  9. H. Zheng, Y. Wu, L. Deng, Y. Hu, and G. Li, “Going deeper with directly-trained larger spiking neural networks,” in Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), vol. 35, no. 12, 2021, pp. 11 062–11 070.
  10. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
  11. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  12. Y. Li, Y. Guo, S. Zhang, S. Deng, Y. Hai, and S. Gu, “Differentiable spike: Rethinking gradient-descent for training spiking neural networks,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 34, 2021.
  13. W. Fang, Z. Yu, Y. Chen, T. Huang, T. Masquelier, and Y. Tian, “Deep residual learning in spiking neural networks,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 34, 2021.
  14. S. Deng, Y. Li, S. Zhang, and S. Gu, “Temporal efficient training of spiking neural network via gradient re-weighting,” arXiv preprint arXiv:2202.11946, 2022.
  15. L. Zhu, X. Wang, Y. Chang, J. Li, T. Huang, and Y. Tian, “Event-based video reconstruction via potential-assisted spiking neural network,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 3594–3604.
  16. J. Hagenaars, F. Paredes-Vallés, and G. De Croon, “Self-supervised learning of event-based optical flow with spiking neural networks,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 34, 2021.
  17. Y. Kim, J. Chough, and P. Panda, “Beyond classification: Directly training spiking neural networks for semantic segmentation,” Neuromorphic Computing and Engineering, vol. 2, no. 4, p. 044015, 2022.
  18. V. B. Mountcastle, “The columnar organization of the neocortex.” Brain: a Journal of Neurology, vol. 120, no. 4, pp. 701–722, 1997.
  19. H. Liang, X. Gong, M. Chen, Y. Yan, W. Li, and C. D. Gilbert, “Interactions between feedback and lateral connections in the primary visual cortex,” Proceedings of the National Academy of Sciences, vol. 114, no. 32, pp. 8637–8642, 2017.
  20. T. Elsken, J. H. Metzen, and F. Hutter, “Neural architecture search: A survey,” The Journal of Machine Learning Research, vol. 20, no. 1, pp. 1997–2017, 2019.
  21. Y. Liu, Y. Sun, B. Xue, M. Zhang, G. G. Yen, and K. C. Tan, “A survey on evolutionary neural architecture search,” IEEE Transactions on Neural Networks and Learning Systems, 2021.
  22. B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, “Learning transferable architectures for scalable image recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8697–8710.
  23. B. Zoph and Q. V. Le, “Neural architecture search with reinforcement learning,” arXiv preprint arXiv:1611.01578, 2016.
  24. C. Liu, L.-C. Chen, F. Schroff, H. Adam, W. Hua, A. L. Yuille, and L. Fei-Fei, “Auto-deeplab: Hierarchical neural architecture search for semantic image segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 82–92.
  25. H. Liu, K. Simonyan, and Y. Yang, “Darts: Differentiable architecture search,” in Proceedings of International Conference on Learning Representations (ICLR), 2018.
  26. M. E. Hasselmo and C. E. Stern, “Mechanisms underlying working memory for novel information,” Trends in Cognitive Sciences, vol. 10, no. 11, pp. 487–493, 2006.
  27. K. H. Shankar and M. W. Howard, “A scale-invariant internal representation of time,” Neural Computation, vol. 24, no. 1, pp. 134–193, 2012.
  28. A. Z. Zhu, D. Thakur, T. Özaslan, B. Pfrommer, V. Kumar, and K. Daniilidis, “The multivehicle stereo event camera dataset: An event camera dataset for 3d perception,” IEEE Robotics and Automation Letters, vol. 3, no. 3, pp. 2032–2039, 2018.
  29. M. A. Petrovici, J. Bill, I. Bytschok, J. Schemmel, and K. Meier, “Stochastic inference with spiking neurons in the high-conductance state,” Physical Review E, vol. 94, no. 4, p. 042312, 2016.
  30. E. Neftci, S. Das, B. Pedroni, K. Kreutz-Delgado, and G. Cauwenberghs, “Event-driven contrastive divergence for spiking neuromorphic systems,” Frontiers in Neuroscience, vol. 7, p. 272, 2014.
  31. L. Leng, R. Martel, O. Breitwieser, I. Bytschok, W. Senn, J. Schemmel, K. Meier, and M. A. Petrovici, “Spiking neurons with short-term synaptic plasticity form superior generative networks,” Scientific Reports, vol. 8, no. 1, pp. 1–11, 2018.
  32. M. Mozafari, S. R. Kheradpisheh, T. Masquelier, A. Nowzari-Dalini, and M. Ganjtabesh, “First-spike-based visual categorization using reward-modulated stdp,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 12, pp. 6178–6190, 2018.
  33. L. Leng, “Solving machine learning problems with biological principles,” Ph.D. dissertation, 2020.
  34. A. Korcsak-Gorzo, M. G. Müller, A. Baumbach, L. Leng, O. J. Breitwieser, S. J. van Albada, W. Senn, K. Meier, R. Legenstein, and M. A. Petrovici, “Cortical oscillations support sampling-based computations in spiking neural networks,” PLoS Computational Biology, vol. 18, no. 3, p. e1009753, 2022.
  35. G. Bellec, F. Scherr, A. Subramoney, E. Hajek, D. Salaj, R. Legenstein, and W. Maass, “A solution to the learning dilemma for recurrent networks of spiking neurons,” Nature Communications, vol. 11, no. 1, pp. 1–15, 2020.
  36. B. Rueckauer, I.-A. Lungu, Y. Hu, M. Pfeiffer, and S.-C. Liu, “Conversion of continuous-valued deep networks to efficient event-driven networks for image classification,” Frontiers in Neuroscience, vol. 11, p. 682, 2017.
  37. T. Bu, W. Fang, J. Ding, P. Dai, Z. Yu, and T. Huang, “Optimal ann-snn conversion for high-accuracy and ultra-low-latency spiking neural networks,” in Proceedings of International Conference on Learning Representations (ICLR), 2021.
  38. Y. Li, S. Deng, X. Dong, R. Gong, and S. Gu, “A free lunch from ann: Towards efficient, accurate spiking neural networks calibration,” in Proceedings of International Conference on Machine Learning (ICML).   PMLR, 2021, pp. 6316–6325.
  39. J. Wu, C. Xu, X. Han, D. Zhou, M. Zhang, H. Li, and K. C. Tan, “Progressive tandem learning for pattern recognition with deep spiking neural networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 7824–7840, 2021.
  40. Y. Bengio, N. Léonard, and A. Courville, “Estimating or propagating gradients through stochastic neurons for conditional computation,” arXiv preprint arXiv:1308.3432, 2013.
  41. P. Yin, J. Lyu, S. Zhang, S. Osher, Y. Qi, and J. Xin, “Understanding straight-through estimator in training activation quantized neural nets,” in Proceedings of International Conference on Learning Representations (ICLR), 2019.
  42. F. Zenke and T. P. Vogels, “The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks,” Neural Computation, vol. 33, no. 4, pp. 899–925, 2021.
  43. S. Lian, J. Shen, Q. Liu, Z. Wang, R. Yan, and H. Tang, “Learnable surrogate gradient for direct training spiking neural networks.” in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2023, pp. 3002–3010.
  44. C. Liu, B. Zoph, M. Neumann, J. Shlens, W. Hua, L.-J. Li, L. Fei-Fei, A. Yuille, J. Huang, and K. Murphy, “Progressive neural architecture search,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 19–34.
  45. E. Real, A. Aggarwal, Y. Huang, and Q. V. Le, “Regularized evolution for image classifier architecture search,” in Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), vol. 33, no. 01, 2019, pp. 4780–4789.
  46. Y. Chen, T. Yang, X. Zhang, G. Meng, X. Xiao, and J. Sun, “Detnas: Backbone search for object detection,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 32, 2019.
  47. J. Guo, K. Han, Y. Wang, C. Zhang, Z. Yang, H. Wu, X. Chen, and C. Xu, “Hit-detector: Hierarchical trinity architecture search for object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 11 405–11 414.
  48. V. Nekrasov, H. Chen, C. Shen, and I. Reid, “Fast neural architecture search of compact semantic segmentation models via auxiliary cells,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9126–9135.
  49. P. Lin, P. Sun, G. Cheng, S. Xie, X. Li, and J. Shi, “Graph-guided architecture search for real-time semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 4203–4212.
  50. Y. Xu, L. Xie, X. Zhang, X. Chen, G.-J. Qi, Q. Tian, and H. Xiong, “Pc-darts: Partial channel connections for memory-efficient architecture search,” in Proceedings of International Conference on Learning Representations (ICLR), 2019.
  51. X. Chen, L. Xie, J. Wu, and Q. Tian, “Progressive differentiable architecture search: Bridging the depth gap between search and evaluation,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 1294–1303.
  52. X. Chu, X. Wang, B. Zhang, S. Lu, X. Wei, and J. Yan, “Darts-: Robustly stepping out of performance collapse without indicators,” in Proceedings of International Conference on Learning Representations (ICLR), 2020.
  53. X. Cheng, Y. Zhong, M. Harandi, Y. Dai, X. Chang, H. Li, T. Drummond, and Z. Ge, “Hierarchical neural architecture search for deep stereo matching,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 22 158–22 169, 2020.
  54. S. Shen, R. Zhang, C. Wang, R. Huang, A. Tuerhong, Q. Guo, Z. Lu, J. Zhang, and L. Leng, “Evolutionary spiking neural networks: a survey,” Journal of Membrane Computing, pp. 1–12, 2024.
  55. B. Na, J. Mok, S. Park, D. Lee, H. Choe, and S. Yoon, “Autosnn: Towards energy-efficient spiking neural networks,” in Proceedings of International Conference on Machine Learning (ICML).   PMLR, 2022, pp. 16 253–16 269.
  56. Y. Kim, Y. Li, H. Park, Y. Venkatesha, and P. Panda, “Neural architecture search for spiking neural networks,” in Proceedings of the European Conference on Computer Vision (ECCV).   Springer, 2022, pp. 36–56.
  57. G. Wang, Y. Sun, S. Cheng, and S. Song, “Evolving connectivity for recurrent spiking neural networks,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 2991–3007, 2023.
  58. A. Gaier and D. Ha, “Weight agnostic neural networks,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 32, 2019.
  59. G. Shen, D. Zhao, Y. Dong, and Y. Zeng, “Brain-inspired neural circuit evolution for spiking neural networks,” Proceedings of the National Academy of Sciences, vol. 120, no. 39, p. e2218173120, 2023.
  60. Z. Xie, Z. Liu, P. Chen, and J. Zhang, “Efficient spiking neural architecture search with mixed neuron models and variable thresholds,” in International Conference on Neural Information Processing (ICONIP).   Springer, 2023, pp. 466–481.
  61. S. Yan, Q. Meng, M. Xiao, Y. Wang, and Z. Lin, “Sampling complex topology structures for spiking neural networks,” Neural Networks, vol. 172, p. 106121, 2024.
  62. J. Yan, Q. Liu, M. Zhang, L. Feng, D. Ma, H. Li, and G. Pan, “Efficient spiking neural network design via neural architecture search,” Neural Networks, vol. 173, p. 106172, 2024.
  63. R. Zimmer, T. Pellegrini, S. F. Singh, and T. Masquelier, “Technical report: supervised training of convolutional spiking neural networks with pytorch,” arXiv preprint arXiv:1911.10124, 2019.
  64. Z. Wu, H. Zhang, Y. Lin, G. Li, M. Wang, and Y. Tang, “Liaf-net: Leaky integrate and analog fire network for lightweight and efficient spatiotemporal information processing,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 11, pp. 6249–6262, 2021.
  65. W. Fang, Z. Yu, Y. Chen, T. Masquelier, T. Huang, and Y. Tian, “Incorporating learnable membrane time constant to enhance learning of spiking neural networks,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 2661–2671.
  66. Z. Yang, Y. Wu, G. Wang, Y. Yang, G. Li, L. Deng, J. Zhu, and L. Shi, “Dashnet: A hybrid artificial and spiking neural network for high-speed object tracking,” arXiv preprint arXiv:1909.12942, 2019.
  67. C. Lee, A. K. Kosta, A. Z. Zhu, K. Chaney, K. Daniilidis, and K. Roy, “Spike-flownet: event-based optical flow estimation with energy-efficient hybrid neural networks,” in Proceedings of the European Conference on Computer Vision (ECCV).   Springer, 2020, pp. 366–382.
  68. X. Chen, Q. Yang, J. Wu, H. Li, and K. C. Tan, “A hybrid neural coding approach for pattern recognition with spiking neural networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 5, pp. 3064–3078, 2024.
  69. G. Gallego, T. Delbrück, G. Orchard, C. Bartolozzi, B. Taba, A. Censi, S. Leutenegger, A. J. Davison, J. Conradt, K. Daniilidis et al., “Event-based vision: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 1, pp. 154–180, 2020.
  70. P. A. Merolla, J. V. Arthur, R. Alvarez-Icaza, A. S. Cassidy, J. Sawada, F. Akopyan, B. L. Jackson, N. Imam, C. Guo, Y. Nakamura et al., “A million spiking-neuron integrated circuit with a scalable communication network and interface,” Science, vol. 345, no. 6197, pp. 668–673, 2014.
  71. K. Roy, A. Jaiswal, and P. Panda, “Towards spike-based machine intelligence with neuromorphic computing,” Nature, vol. 575, no. 7784, pp. 607–617, 2019.
  72. L. Zhu, S. Dong, J. Li, T. Huang, and Y. Tian, “Ultra-high temporal resolution visual reconstruction from a fovea-like spike camera via spiking neuron model,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 1233–1249, 2023.
  73. R. W. Baldwin, R. Liu, M. Almatrafi, V. Asari, and K. Hirakawa, “Time-ordered recent event (tore) volumes for event cameras,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 2, pp. 2519–2532, 2023.
  74. Y. Zheng, L. Zheng, Z. Yu, T. Huang, and S. Wang, “Capture the moment: High-speed imaging with spiking cameras through short-term plasticity,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 7, pp. 8127–8142, 2023.
  75. A. Kugele, T. Pfeil, M. Pfeiffer, and E. Chicca, “Efficient processing of spatio-temporal data streams with spiking neural networks,” Frontiers in Neuroscience, vol. 14, p. 439, 2020.
  76. B. Li, L. Leng, S. Shen, K. Zhang, J. Zhang, J. Liao, and R. Cheng, “Efficient deep spiking multilayer perceptrons with multiplication-free inference,” IEEE Transactions on Neural Networks and Learning Systems, 2024.
  77. S. Kim, S. Park, B. Na, and S. Yoon, “Spiking-yolo: Spiking neural network for energy-efficient object detection,” in Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), vol. 34, no. 07, 2020, pp. 11 270–11 277.
  78. H. Zhang, Y. Li, L. Leng, K. Che, Q. Liu, Q. Guo, J. Liao, and R. Cheng, “Automotive object detection via learning sparse events by spiking neurons,” IEEE Transactions on Cognitive and Developmental Systems, 2024.
  79. R. Zhang, L. Leng, K. Che, H. Zhang, J. Cheng, Q. Guo, J. Liao, and R. Cheng, “Accurate and efficient event-based semantic segmentation using adaptive spiking encoder–decoder network,” IEEE Transactions on Neural Networks and Learning Systems, 2024.
  80. F. Paredes-Vallés, K. Y. W. Scheper, and G. C. H. E. de Croon, “Unsupervised learning of a hierarchical spiking neural network for optical flow estimation: From events to global motion perception,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 8, pp. 2051–2064, 2020.
  81. S. Liu and P. L. Dragotti, “Sensing diversity and sparsity models for event generation and video reconstruction from events,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 10, pp. 12 444–12 458, 2023.
  82. A. Z. Zhu, Y. Chen, and K. Daniilidis, “Realtime time synchronized event-based stereo,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 433–447.
  83. Y. Zhou, G. Gallego, H. Rebecq, L. Kneip, H. Li, and D. Scaramuzza, “Semi-dense 3d reconstruction with a stereo event camera,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 235–251.
  84. S. Tulyakov, F. Fleuret, M. Kiefel, P. Gehler, and M. Hirsch, “Learning an event sequence embedding for dense event-based deep stereo,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 1527–1537.
  85. S. H. Ahmed, H. W. Jang, S. N. Uddin, and Y. J. Jung, “Deep event stereo leveraged by event-to-image translation,” in Proceedings of Association for the Advancement of Artificial Intelligence (AAAI), vol. 35, no. 2, 2021, pp. 882–890.
  86. M. Mostafavi, K.-J. Yoon, and J. Choi, “Event-intensity stereo: Estimating depth by the best of both worlds,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 4258–4267.
  87. K. Zhang, K. Che, J. Zhang, J. Cheng, Z. Zhang, Q. Guo, and L. Leng, “Discrete time convolution for fast event-based stereo,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 8676–8686.
  88. U. Rançon, J. Cuadrado-Anibarro, B. R. Cottereau, and T. Masquelier, “Stereospike: Depth learning with a spiking neural network,” IEEE Access, vol. 10, pp. 127 428–127 439, 2022.
  89. G. Bellec, D. Salaj, A. Subramoney, R. Legenstein, and W. Maass, “Long short-term memory and learning-to-learn in networks of spiking neurons,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 31, 2018.
  90. F. Zenke and S. Ganguli, “Superspike: Supervised learning in multilayer spiking neural networks,” Neural Computation, vol. 30, no. 6, pp. 1514–1541, 2018.
  91. S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proceedings of International Conference on Machine Learning (ICML).   PMLR, 2015, pp. 448–456.
  92. J. Pei, L. Deng, S. Song, M. Zhao, and L. Shi, “Towards artificial general intelligence with hybrid tianjic chip architecture,” Nature, vol. 572, no. 7767, p. 106, 2019.
  93. M. Horowitz, “1.1 computing’s energy problem (and what we can do about it),” in IEEE International Solid-state Circuits Conference Digest of Technical Papers (ISSCC).   IEEE, 2014, pp. 10–14.
  94. S. Tulyakov, A. Ivanov, and F. Fleuret, “Practical deep stereo (pds): Toward applications-friendly deep stereo matching,” Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol. 31, 2018.
  95. L. Wang, Y.-S. Ho, K.-J. Yoon et al., “Event-based high dynamic range image and very high frame rate video generation using conditional generative adversarial networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10 081–10 090.
  96. A. Krizhevsky, V. Nair, and G. Hinton, “Cifar-10 (canadian institute for advanced research).” [Online]. Available: http://www.cs.toronto.edu/ kriz/cifar.html
  97. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   Ieee, 2009, pp. 248–255.
  98. J. Wu, Y. Chua, M. Zhang, G. Li, H. Li, and K. C. Tan, “A tandem learning rule for effective training and rapid inference of deep spiking neural networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 1, pp. 446–460, 2021.
  99. V. Sovrasov. (2019) Flops counter for convolutional networks in pytorch framework. [Online]. Available: https://github.com/sovrasov/flops-counter.pytorch/

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free