{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T08:30:22Z","timestamp":1782981022565,"version":"3.54.5"},"reference-count":42,"publisher":"MIT Press - Journals","issue":"9","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Learning new concepts rapidly from a few examples is an open issue in spike-based machine learning. This few-shot learning imposes substantial challenges to the current learning methodologies of spiking neuron networks (SNNs) due to the lack of task-related priori knowledge. The recent learning-to-learn (L2L) approach allows SNNs to acquire priori knowledge through example-level learning and task-level optimization. However, existing L2L-based frameworks do not target the neural dynamics (i.e., neuronal and synaptic parameter changes) on different timescales. This diversity of temporal dynamics is an important attribute in spike-based learning, which facilitates the networks to rapidly acquire knowledge from very few examples and gradually integrate this knowledge. In this work, we consider the neural dynamics on various timescales and provide a multi-timescale optimization (MTSO) framework for SNNs. This framework introduces an adaptive-gated LSTM to accommodate two different timescales of neural dynamics: short-term learning and long-term evolution. Short-term learning is a fast knowledge acquisition process achieved by a novel surrogate gradient online learning (SGOL) algorithm, where the LSTM guides gradient updating of SNN on a short timescale through an adaptive learning rate and weight decay gating. The long-term evolution aims to slowly integrate acquired knowledge and form a priori, which can be achieved by optimizing the LSTM guidance process to tune SNN parameters on a long timescale. Experimental results demonstrate that the collaborative optimization of multi-timescale neural dynamics can make SNNs achieve promising performance for the few-shot learning tasks.<\/jats:p>","DOI":"10.1162\/neco_a_01423","type":"journal-article","created":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T20:44:54Z","timestamp":1626727494000},"page":"2439-2472","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":18,"title":["Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization"],"prefix":"10.1162","volume":"33","author":[{"given":"Runhao","family":"Jiang","sequence":"first","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu 610065, China 15520816169@163.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu 610065, China iejiezhang@163.com"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University of Technology, Hangzhou 310014, China ryan@zjut.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huajin","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China, and Zhejiang Lab, Hangzhou 311121, China htang@zju.edu.cn"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"key":"2021081922220952000_B1","doi-asserted-by":"crossref","unstructured":"Amir, A., Taba, B., Berg, D., Melano, T., & Modha, D. (2017). A low power, fully event-based gesture recognition system. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (pp. 7388\u20137397). Piscataway, NJ: IEEE.","DOI":"10.1109\/CVPR.2017.781"},{"key":"2021081922220952000_B2","first-page":"3981","volume-title":"Advances in neural information processing systems, 29","author":"Andrychowicz","year":"2016"},{"key":"2021081922220952000_B3","first-page":"787","volume-title":"Advances in neural information processing systems","author":"Bellec","year":"2018"},{"key":"2021081922220952000_B4","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2019.00483","article-title":"Neuromorphic hardware learns to learn","volume":"13","author":"Bohnstingl","year":"2019","journal-title":"Frontiers in Neuroscience"},{"issue":"12","key":"2021081922220952000_B5","doi-asserted-by":"crossref","first-page":"2557","DOI":"10.1162\/neco_a_01319","article-title":"Analyzing and accelerating the bottlenecks of training deep SNNs with backpropagation","volume":"32","author":"Chen","year":"2020","journal-title":"Neural Computation"},{"key":"2021081922220952000_B6","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.neunet.2019.09.005","article-title":"Rethinking the performance comparison between SNNS and ANNS","volume":"121","author":"Deng","year":"2020","journal-title":"Neural Networks"},{"key":"2021081922220952000_B7","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2015.00099","article-title":"Unsupervised learning of digit recognition using spike-timing-dependent plasticity","volume":"9","author":"Diehl","year":"2015","journal-title":"Frontiers in Computational Neuroscience"},{"key":"2021081922220952000_B8","unstructured":"Fefei, L., Fergus, & Perona (2003). A Bayesian approach to unsupervised one-shot learning of object categories. In Proceedings of the Ninth IEEE International Conference on Computer Vision (pp. 1134\u20131141). Piscataway, NJ: IEEE."},{"key":"2021081922220952000_B9","unstructured":"Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning, vol. 70 (pp. 1126\u20131135)."},{"issue":"4","key":"2021081922220952000_B10","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1142\/S0129065709002002","article-title":"Spiking neural networks","volume":"19","author":"Ghosh-Dastidar","year":"2009","journal-title":"International Journal of Neural Systems"},{"key":"2021081922220952000_B11","doi-asserted-by":"crossref","unstructured":"Gu, P., Xiao, R., Pan, G., & Tang, H. (2019). STCA: Spatio-temporal credit assignment with delayed feedback in deep spiking neural networks. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (pp. 1366\u20131372).","DOI":"10.24963\/ijcai.2019\/189"},{"key":"2021081922220952000_B12","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Younger, S. A., & Conwell, R. P. (2001). Learning to learn using gradient descent. In Proceedings of the International Conference on Artificial Neural Networks (pp. 87\u201394). Berlin: Springer.","DOI":"10.1007\/3-540-44668-0_13"},{"key":"2021081922220952000_B13","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1016\/j.neucom.2016.04.029","article-title":"Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition","volume":"205","author":"Kheradpisheh","year":"2016","journal-title":"Neurocomputing"},{"key":"2021081922220952000_B14","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980."},{"key":"2021081922220952000_B15","unstructured":"Koch, G., Zemel, R., & Salakhutdinov, R. (2015). Siamese neural networks for one-shot image recognition. In Proceedings of the International Conference on Machine Learning, vol. 2."},{"key":"2021081922220952000_B16","unstructured":"Lake, B., Salakhutdinov, R., Gross, J., & Tenenbaum, J. (2011). One shot learning of simple visual concepts. In Proceedings of the Annual Meeting of the Cognitive Science Society. Red Hook, NY: Curran."},{"issue":"6266","key":"2021081922220952000_B17","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1126\/science.aab3050","article-title":"Human-level concept learning through probabilistic program induction","volume":"350","author":"Lake","year":"2015","journal-title":"Science"},{"key":"2021081922220952000_B18","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2016.00508","article-title":"Training deep spiking neural networks using backpropagation","volume":"10","author":"Lee","year":"2016","journal-title":"Frontiers in Neuroscience"},{"issue":"9","key":"2021081922220952000_B19","doi-asserted-by":"crossref","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","article-title":"Networks of spiking neurons: The third generation of neural network models","volume":"10","author":"Maass","year":"1997","journal-title":"Neural Networks"},{"issue":"11","key":"2021081922220952000_B20","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2021081922220952000_B21","unstructured":"Munkhdalai, T., & Yu, H. (2017). Meta networks. In Proceedings of the 34th International Conference on Machine Learning, vol. 70 (p. 2554)."},{"key":"2021081922220952000_B22","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Processing Magazine"},{"key":"2021081922220952000_B23","unstructured":"Nichol, A., & Schulman, J. (2018). Reptile: A scalable metalearning algorithm. arXiv:1803.02999, 2, 2."},{"key":"2021081922220952000_B24","unstructured":"Nitin, R., Gopalakrishnan, S., Priyadarshini, P., & Kaushik, R. (2020). Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation. In Proceedings of the Eighth International Conference on Learning Representations."},{"key":"2021081922220952000_B25","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., \u2026 Chintala, S. (2019). Pytorch: An imperative style, high- performance deep learning library. In Advances in neural information processing systems, 32 (pp. 8026\u20138037). Red Hook, NY: Curran."},{"key":"2021081922220952000_B26","unstructured":"Ravi, S., & Larochelle (2017). Optimization as a model for few-shot learning. In Proceedings of the 5th International Conference on Learning Representations."},{"issue":"3","key":"2021081922220952000_B27","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1162\/NECO_a_00929","article-title":"Deep learning with dynamic spiking neurons and fixed feedback weights","volume":"29","author":"Samadi","year":"2017","journal-title":"Neural Computation"},{"key":"2021081922220952000_B28","unstructured":"Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016). Meta- learning with memory-augmented neural networks. In Proceedings of the 33rd International Conference on Machine Learning, vol. 48 (pp. 1842\u20131850)."},{"issue":"1","key":"2021081922220952000_B29","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1023\/A:1007383707642","article-title":"Shifting inductive bias with success- story algorithm, adaptive Levin search, and incremental self-improvement","volume":"28","author":"Schmidhuber","year":"1997","journal-title":"Machine Learning"},{"key":"2021081922220952000_B30","first-page":"1412","volume-title":"Advances in neural information processing systems","author":"Shrestha","year":"2018"},{"key":"2021081922220952000_B31","first-page":"4077","volume-title":"Advances in neural information processing systems","author":"Snell","year":"2017"},{"key":"2021081922220952000_B32","doi-asserted-by":"crossref","unstructured":"Stewart, K., Orchard, G., Shrestha, S. B., & Neftci, E. (2020). On-chip few-shot learning with surrogate gradient descent on a neuromorphic processor. In Proceedings of the Second IEEE International Conference on Artificial Intelligence Circuits and Systems (pp. 223\u2013227). Piscataway, NJ: IEEE.","DOI":"10.1109\/AICAS48895.2020.9073948"},{"key":"2021081922220952000_B33","first-page":"1199","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sung","year":"2018"},{"key":"2021081922220952000_B34","doi-asserted-by":"crossref","unstructured":"Thrun, S.\n           (1998). Learning to learn. Berlin: Springer.","DOI":"10.1007\/978-1-4615-5529-2"},{"key":"2021081922220952000_B35","unstructured":"Vanschoren, J.\n           (2018). Meta-learning: A survey. arXiv: abs\/1810.03548."},{"key":"2021081922220952000_B36","first-page":"3630","volume-title":"Advances in neural information processing systems","author":"Vinyals","year":"2016"},{"key":"2021081922220952000_B37","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2020.00199","article-title":"Deep spiking neural networks for large vocabulary automatic speech recognition","volume":"14","author":"Wu","year":"2020","journal-title":"Frontiers in Neuroscience"},{"key":"2021081922220952000_B38","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2018.00331","article-title":"Spatio-temporal backpropagation for training high-performance spiking neural networks","volume":"12","author":"Wu","year":"2018","journal-title":"Frontiers in Neuroscience"},{"key":"2021081922220952000_B39","doi-asserted-by":"crossref","unstructured":"Xiao, R., Yu, Q., Yan, R., & Tang, H. (2019). Fast and accurate classification with a multi-spike learning algorithm for spiking neurons. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (pp. 1445\u20131451).","DOI":"10.24963\/ijcai.2019\/200"},{"key":"2021081922220952000_B40","doi-asserted-by":"crossref","unstructured":"Yu, Q., Li, S., Tang, H., Wang, L., Dang, J., & Tan, C. K. (2020). Toward efficient processing and learning with spikes: New approaches for multispike learning.IEEE Transactions on Systems, Man, and Cybernetics (pp. 1\u201313). Piscataway, NJ: IEEE.","DOI":"10.1109\/TCYB.2020.2984888"},{"issue":"6","key":"2021081922220952000_B41","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1162\/neco_a_01086","article-title":"Superspike: Supervised learning in multi-layer spiking neural networks","volume":"30","author":"Zenke","year":"2018","journal-title":"Neural Computation"},{"issue":"3","key":"2021081922220952000_B42","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1109\/JSTSP.2020.2983547","article-title":"An efficient threshold-driven aggregate-label learning algorithm for multimodal information processing","volume":"14","author":"Zhang","year":"2020","journal-title":"IEEE Journal of Selected Topics in Signal Processing"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/9\/2439\/1958011\/neco_a_01423.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/9\/2439\/1958011\/neco_a_01423.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T22:23:04Z","timestamp":1629411784000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/33\/9\/2439\/103015\/Few-Shot-Learning-in-Spiking-Neural-Networks-by"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,19]]},"references-count":42,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,8,19]]},"published-print":{"date-parts":[[2021,8,19]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01423","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9]]},"published":{"date-parts":[[2021,8,19]]}}}