Robust SpikeBased Continual MetaLearning Improved by Restricted Minimum Error Entropy Criterion
Abstract
:1. Introduction
2. Materials and Methods
2.1. SNN Model
2.2. BPTT Training Algorithm
2.3. Minimum Error Entropy Criterion (MEEC)
2.4. Restricted MEEC
3. Results
3.1. Proposed Network with RMEE Criterion
3.2. Autonomous Navigation
Algorithm 1 Training process in the reward learning process 
Input: number of full episodes $K$, timesteps $T$, fixed parameters ${\mathsf{\theta}}_{\mathit{o}\mathit{l}\mathit{d}}$, target firing rate ${\mathit{f}}^{\mathit{0}}$, regularization hyperparameters ${\mu}_{v}$, ${\mu}_{e}$, ${\mu}_{firing}$, bandwidth $\mathit{\sigma}$, predicted value function ${V}_{\mathsf{\theta}}\left(\mathit{t},\mathit{k}\right)$ and sum of future rewards $R\left(t,k\right)$ Output: total loss ${\mathit{L}}_{\mathsf{\theta}}$.

3.3. Working Memory Performance on Store–Recall Task with NonGaussian Noise
3.4. MetaLearning Performance on Sequential MNIST Data Set with NonGaussian Noise
3.5. Effects of Loss Parameters on Learning Performance
4. Discussion
5. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
 Krizhevsky, A.; Sutskever, I.; Hinton, G. ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 2012, 25, 89–94. [Google Scholar] [CrossRef]
 Parisi, G.I.; Kemker, R.; Part, J.L.; Kanan, C.; Wermter, S. Continual lifelong learning with neural networks: A review. Neural Netw. 2019, 113, 54–71. [Google Scholar] [CrossRef] [PubMed]
 Yao, H.; Zhou, Y.; Mahdavi, M.; Li, Z.; Socher, R.; Xiong, C. Online structured metalearning. Adv. Neural Inf. Process. Syst. 2020, 33, 6779–6790. [Google Scholar]
 Javed, K.; White, M. Metalearning representations for continual learning. Adv. Neural Inf. Process. Syst. 2019, 32, 172. [Google Scholar]
 Serrà, J.; Surís, D.; Miron, M.; Karatzoglou, A. Overcoming catastrophic forgetting with hard attention to the task. In Proceedings of the International Conference on Machine Learning (PMLR 80), Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018; pp. 4548–4557. [Google Scholar]
 Zeng, G.; Chen, Y.; Cui, B.; Yu, S. Continual learning of contextdependent processing in neural networks. Nat. Mach. Intell. 2019, 1, 364–372. [Google Scholar] [CrossRef]
 van de Ven, G.M.; Siegelmann, H.T.; Tolias, A.S. Braininspired replay for continual learning with artificial neural networks. Nat. Commun. 2020, 11, 4069. [Google Scholar] [CrossRef]
 Tavanaei, A.; Ghodrati, M.; Kheradpisheh, S.R.; Masquelier, T.; Maida, A. Deep learning in spiking neural networks. Neural Netw. 2019, 111, 47–63. [Google Scholar] [CrossRef] [Green Version]
 Lee, C.; Panda, P.; Srinivasan, G.; Roy, K. Training deep spiking convolutional neural networks with stdpbased unsupervised pretraining followed by supervised finetuning. Front. Neurosci. 2018, 12, 435. [Google Scholar] [CrossRef]
 Xia, Q.; Yang, J.J. Memristive crossbar arrays for braininspired computing. Nat. Mat. 2019, 18, 309–323. [Google Scholar] [CrossRef]
 Pei, J.; Deng, L.; Song, S.; Zhao, M.; Zhang, Y.; Wu, S.; Wang, G.; Zou, Z.; Wu, Z.; He, W.; et al. Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 2019, 572, 106–111. [Google Scholar] [CrossRef]
 Davies, M.; Srinivasa, N.; Lin, T.H.; Chinya, G.; Cao, Y.; Choday, S.H.; Dimou, G.; Joshi, P.; Imam, N.; Jain, S.; et al. Loihi: A neuromorphic manycore processor with onchip learning. IEEE Micro 2018, 38, 82–99. [Google Scholar] [CrossRef]
 Yang, S.; Wang, J.; Hao, X.; Li, H.; Wei, X.; Deng, B.; Loparo, K.A. BiCoSS: Toward largescale cognition brain with multigranular neuromorphic architecture. IEEE Trans. Neural Netw. Learn. Syst. 2021, 11, 1–15. [Google Scholar] [CrossRef] [PubMed]
 Yang, S.; Wang, J.; Zhang, N.; Deng, B.; Pang, Y.; Azghadi, M.R. Cerebellumorphic: Largescale neuromorphic model and architecture for supervised motor learning. IEEE Trans. Neural Netw. Learn. Syst. 2021, 23, 1–15. [Google Scholar] [CrossRef] [PubMed]
 Yang, S.; Wang, J.; Deng, B.; Liu, C.; Li, H.; Fietkiewicz, C.; Loparo, K.A. Realtime neuromorphic system for largescale conductancebased spiking neural networks. IEEE Trans. Cybern. 2019, 49, 2490–2503. [Google Scholar] [CrossRef]
 Bellec, G.; Salaj, D.; Subramoney, A.; Legenstein, R.; Maass, W. Long shortterm memory and learningtolearn in networks of spiking neurons. Adv. Neural Inf. Process. Syst. 2018, 31, 247. [Google Scholar]
 Li, Y.; Zhou, J.; Tian, J.; Zheng, X.; Tang, Y.Y. Weighted error entropybased information theoretic learning for robust subspace representation. IEEE Trans. Neural Netw. Learn. Syst. 2021, 19, 1–15. [Google Scholar] [CrossRef]
 Chen, J.; Song, L.; Wainwright, M.; Jordan, M. Learning to explain: An informationtheoretic perspective on model interpretation. In Proceedings of the 35th International Conference on Machine Learning (PMLR 80), Stockholmsmässan, Stockholm, Sweden, 10–15 July 2018; pp. 883–892. [Google Scholar]
 Xu, Y.; Cao, P.; Kong, Y.; Wang, Y. DMI: A novel informationtheoretic loss function for training deep nets robust to label noise. Adv. Neural Inf. Process. Syst. 2019, 32, 76. [Google Scholar]
 Chen, B.; Xing, L.; Zhao, H.; Du, S.; Principe, J.C. Effects of outliers on the maximum correntropy estimation: A robustness analysis. IEEE Trans. Syst. Man Cybern. Syst. 2021, 51, 4007–4012. [Google Scholar] [CrossRef]
 Chen, B.; Li, Y.; Dong, J.; Lu, N.; Qin, J. Common spatial patterns based on the quantized minimum error entropy criterion. IEEE Trans. Syst. Man Cybern. Syst. 2020, 50, 4557–4568. [Google Scholar] [CrossRef]
 Chen, B.; Xing, L.; Xu, B.; Zhao, H.; Principe, J.C. Insights into the robustness of minimum error entropy estimation. IEEE Trans. Neural Netw. Learn. Syst. 2018, 29, 731–737. [Google Scholar] [CrossRef]
 Chen, H.Y.; Liang, J.H.; Chang, S.C.; Pan, J.Y.; Chen, Y.T.; Wei, W.; Juan, D.C. Improving adversarial robustness via guided complement entropy. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October–2 November 2019; pp. 4880–4888. [Google Scholar]
 Rachdi, M.; Waku, J.; Hazgui, H.; Demongeot, J. Entropy as a robustness marker in genetic regulatory networks. Entropy 2020, 22, 260. [Google Scholar] [CrossRef] [PubMed] [Green Version]
 Borin, J.A.M.S.; HumeauHeurtier, A.; Virgílio Silva, L.E.; Murta, L.O. Multiscale entropy analysis of short signals: The robustness of fuzzy entropybased variants compared to fulllength long signals. Entropy 2021, 23, 1620. [Google Scholar] [CrossRef] [PubMed]
 Grienberger, C.; Milstein, A.D.; Bittner, K.C.; Romani, S.; Magee, J.C. Inhibitory suppression of heterogeneously tuned excitation enhances spatial coding in CA1 place cells. Nat. Neurosci. 2017, 20, 417–426. [Google Scholar] [CrossRef]
 Muñoz, W.; Tremblay, R.; Levenstein, D.; Rudy, B. Layerspecific modulation of neocortical dendritic inhibition during active wakefulness. Science 2017, 355, 954–959. [Google Scholar] [CrossRef] [Green Version]
 PolegPolsky, A.; Ding, H.; Diamond, J.S. Functional compartmentalization within starburst amacrine cell dendrites in the retina. Cell Rep. 2018, 22, 2898–2908. [Google Scholar] [CrossRef] [Green Version]
 Ranganathan, G.N.; Apostolides, P.F.; Harnett, M.T.; Xu, N.L.; Druckmann, S.; Magee, J.C. Active dendritic integration and mixed neocortical network representations during an adaptive sensing behavior. Nat. Neurosci. 2018, 21, 1583–1590. [Google Scholar] [CrossRef]
 Bellec, G.; Kappel, D.; Maass, W.; Legenstein, R. Deep rewiring: Training very sparse deep networks. arXiv 2017, arXiv:1711.05136. [Google Scholar]
 Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; Klimov, O. Proximal policy optimization Algorithms. arXiv 2017, arXiv:1707.06347. [Google Scholar]
 Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
 Li, Y.; Chen, B.; Yoshimura, N.; Koike, Y. Restricted minimum error entropy criterion for robust classification. IEEE Trans. Neural Netw. Learn. Syst. 2021, 2, 1–14. [Google Scholar] [CrossRef] [PubMed]
 Vasilaki, E.; Frémaux, N.; Urbanczik, R.; Senn, W.; Gerstner, W. Spikebased reinforcement learning in continuous state and action space: When policy gradient methods fail. PLoS Comput. Biol. 2009, 5, e1000586. [Google Scholar] [CrossRef]
 Wolff, M.J.; Jochim, J.; Akyürek, E.G.; Stokes, M.G. Dynamic hidden states underlying workingmemoryguided behavior. Nat. Neurosci. 2017, 20, 864–871. [Google Scholar] [CrossRef] [PubMed] [Green Version]
 Yang, S.; Gao, T.; Wang, J.; Deng, B.; Lansdell, B.; LinaresBarranco, B. Efficient spikedriven learning with dendritic eventbased processing. Front. Neurosci. 2021, 15, 601109. [Google Scholar] [CrossRef] [PubMed]
 Chen, B.; Zhu, P.; Principe, J.C. Survival information potential: A new criterion for adaptive system training. IEEE Trans. Signal Process. 2012, 60, 1184–1194. [Google Scholar] [CrossRef]
 Jiang, R.; Zhang, J.; Yan, R.; Tang, H. Fewshot learning in spiking neural networks by multitimescale optimization. Neural Comput. 2021, 33, 2439–2472. [Google Scholar] [CrossRef]
 DeBole, M.V.; Appuswamy, R.; Carlson, P.J.; Cassidy, A.S.; Datta, P.; Esser, S.K.; Garreau, G.J.; Holland, K.L.; Lekuch, S.; Mastro, M.; et al. Truenorth: Accelerating from zero to 64 million neurons in 10 years. Computer 2019, 52, 20–29. [Google Scholar] [CrossRef]
 Furber, S.B.; Galluppi, F.; Temple, S.; Plana, L.A. The SpiNNaker project. Proc. IEEE 2014, 102, 652–665. [Google Scholar] [CrossRef]
 Krestinskaya, O.; James, A.P.; Chua, L.O. Neuromemristive circuits for edge computing: A review. IEEE Trans. Neural Netw. Learn. Syst. 2020, 31, 4–23. [Google Scholar] [CrossRef] [Green Version]
 Yoo, J.; Shoaran, M. Neural interface systems with ondevice computing: Machine learning and neuromorphic architectures. Curr. Opin. Biotechnol. 2021, 72, 95–101. [Google Scholar] [CrossRef]
 Cho, S.W.; Kwon, S.M.; Kim, Y.; Park, S.K. Recent progress in transistorbased optoelectronic synapses: From neuromorphic computing to artificial sensory system. Adv. Intell. Syst. 2021, 3, 2000162. [Google Scholar] [CrossRef]
Parameter  Value  Parameter  Value 

R_{m}  1 Ω  R_{i}, R_{e}  1 Ω 
τ_{m}  20 ms  θ_{i}, θ_{e}  0 mV 
κ, κ^{i}, κ^{e}  5 ms  κ^{rec}, κ^{irec}, κ^{erec}  5 ms 
α  1.8  τ^{0}  0.01 
τ_{a}  700 ms  g_{i}, g_{e}  1 nS 
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. 
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, S.; Tan, J.; Chen, B. Robust SpikeBased Continual MetaLearning Improved by Restricted Minimum Error Entropy Criterion. Entropy 2022, 24, 455. https://doi.org/10.3390/e24040455
Yang S, Tan J, Chen B. Robust SpikeBased Continual MetaLearning Improved by Restricted Minimum Error Entropy Criterion. Entropy. 2022; 24(4):455. https://doi.org/10.3390/e24040455
Chicago/Turabian StyleYang, Shuangming, Jiangtong Tan, and Badong Chen. 2022. "Robust SpikeBased Continual MetaLearning Improved by Restricted Minimum Error Entropy Criterion" Entropy 24, no. 4: 455. https://doi.org/10.3390/e24040455