{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:22:54Z","timestamp":1761582174207},"reference-count":37,"publisher":"MIT Press","issue":"5","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recent work on spiking neural networks (SNNs) has focused on achieving deep architectures. They commonly use backpropagation (BP) to train SNNs directly, which allows SNNs to go deeper and achieve higher performance. However, the BP training procedure is computing intensive and complicated by many trainable parameters. Inspired by global pooling in convolutional neural networks (CNNs), we present the spike probabilistic global pooling (SPGP) method based on a probability function for training deep convolutional SNNs. It aims to remove the difficulty of too many trainable parameters brought by multiple layers in the training process, which can reduce the risk of overfitting and get better performance for deep SNNs (DSNNs). We use the discrete leaky-integrate-fire model and the spatiotemporal BP algorithm for training DSNNs directly. As a result, our model trained with the SPGP method achieves competitive performance compared to the existing DSNNs on image and neuromorphic data sets while minimizing the number of trainable parameters. In addition, the proposed SPGP method shows its effectiveness in performance improvement, convergence, and generalization ability.<\/jats:p>","DOI":"10.1162\/neco_a_01480","type":"journal-article","created":{"date-parts":[[2022,3,2]],"date-time":"2022-03-02T00:50:58Z","timestamp":1646182258000},"page":"1170-1188","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":7,"title":["Training Deep Convolutional Spiking Neural Networks With Spike Probabilistic Global Pooling"],"prefix":"10.1162","volume":"34","author":[{"given":"Shuang","family":"Lian","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China 11921058@zju.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianhui","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China qianhuiliu@zju.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University of Technology, Hangzhou 310014, China ryan@zjut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"},{"name":"Zhejiang Lab, Hangzhou 311121, China gpan@zju.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huajin","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"},{"name":"Zhejiang Lab, Hangzhou 311121, China htang@zju.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2022,4,15]]},"reference":[{"key":"2022042221321272100_B1","author":"Aich","year":"2018","journal-title":"Global sum pooling: A generalization trick for object counting with small datasets of large images"},{"key":"2022042221321272100_B2","first-page":"7243","article-title":"A low power, fully event-based gesture recognition system.","author":"Amir","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"2022042221321272100_B3","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.neucom.2019.10.008","article-title":"Impact of fully connected layers on performance of convolutional neural networks for image classification","volume":"378","author":"Basha","year":"2020","journal-title":"Neurocomputing"},{"key":"2022042221321272100_B4","article-title":"Conversion of continuous-valued deep networks to efficient event-driven networks for image classification","volume":"11","author":"Bodo","year":"2017","journal-title":"Frontiers in Neuroscience"},{"issue":"1","key":"2022042221321272100_B5","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s11263-014-0788-3","article-title":"Spiking deep convolutional neural networks for energy-efficient object recognition","volume":"113","author":"Cao","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2022042221321272100_B6","first-page":"1519","article-title":"LISNN: Improving spiking neural networks with lateral interactions for robust object recognition.","author":"Cheng","year":"2020","journal-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence"},{"key":"2022042221321272100_B7","first-page":"1","article-title":"Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing.","author":"Diehl","year":"2015","journal-title":"Proceedings of the 2015 International Joint Conference on Neural Networks"},{"key":"2022042221321272100_B8","author":"Fang","year":"2020","journal-title":"Exploiting neuron and synapse filter dynamics in spatial temporal learning of deep spiking neural network"},{"issue":"7755","key":"2022042221321272100_B9","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1038\/s41586-019-1157-8","article-title":"All-optical spiking neurosynaptic networks with self-learning capabilities","volume":"569","author":"Feldmann","year":"2019","journal-title":"Nature"},{"key":"2022042221321272100_B10","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511815706","author":"Gerstner","year":"2002","journal-title":"Spiking neuron models: Single neurons, populations, plasticity"},{"key":"2022042221321272100_B11","first-page":"1366","article-title":"STCA: Spatio-temporal credit assignment with delayed feedback in deep spiking neural networks.","author":"Gu","year":"2019","journal-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"},{"key":"2022042221321272100_B12","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.neunet.2020.08.001","article-title":"Comparing SNNs and RNNs on neuromorphic vision datasets: Similarities and differences","volume":"132","author":"He","year":"2020","journal-title":"Neural Networks"},{"key":"2022042221321272100_B13","author":"Ioffe","year":"2015","journal-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift."},{"key":"2022042221321272100_B14","first-page":"7005","volume-title":"Advances in neural information processing systems","author":"Jin","year":"2018"},{"key":"2022042221321272100_B15","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00424","article-title":"Synaptic plasticity dynamics for deep continuous local learning (DECOLLE)","volume":"14","author":"Kaiser","year":"2020","journal-title":"Frontiers in Neuroscience"},{"key":"2022042221321272100_B16","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization."},{"key":"2022042221321272100_B17","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"issue":"11","key":"2022042221321272100_B18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"2022042221321272100_B19","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2018.00435","article-title":"Training deep spiking convolutional neural networks with STDP-based unsupervised pre-training followed by supervised fine-tuning","volume":"12","author":"Lee","year":"2018","journal-title":"Frontiers in Neuroscience"},{"key":"2022042221321272100_B20","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2020.00119","article-title":"Enabling spike- based backpropagation for training deep neural network architectures.","volume":"14","author":"Lee","year":"2020","journal-title":"Frontiers in Neuroscience"},{"key":"2022042221321272100_B21","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2017.00309","article-title":"CIFAR10-DVS: An event-stream dataset for object classification","volume":"11","author":"Li","year":"2017","journal-title":"Frontiers in Neuroscience"},{"issue":"2","key":"2022042221321272100_B22","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/JSSC.2007.914337","article-title":"A 128 \u00d7 128 120 DB 15 \u03bcs latency asynchronous temporal contrast vision sensor","volume":"43","author":"Lichtsteiner","year":"2008","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"2022042221321272100_B23","author":"Lin","year":"2013","journal-title":"Network in network"},{"issue":"9","key":"2022042221321272100_B24","doi-asserted-by":"publisher","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"},{"key":"2022042221321272100_B25","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2015.00437","article-title":"Converting static image datasets to spiking neuromorphic datasets using saccades","volume":"9","author":"Orchard","year":"2015","journal-title":"Frontiers in Neuroscience"},{"key":"2022042221321272100_B26","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00774","article-title":"Deep learning with spiking neurons: Opportunities and challenges","volume":"12","author":"Pfeiffer","year":"2018","journal-title":"Frontiers in Neuroscience"},{"key":"2022042221321272100_B27","author":"Rathi","year":"2020","journal-title":"DIET-SNN: Direct input encoding with leakage and threshold optimization in deep spiking neural networks"},{"issue":"7784","key":"2022042221321272100_B28","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"2022042221321272100_B29","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00095","article-title":"Going deeper in spiking neural networks: VGG and residual architectures","volume":"13","author":"Sengupta","year":"2019","journal-title":"Frontiers in Neuroscience"},{"key":"2022042221321272100_B30","first-page":"1412","volume-title":"Advances in neural information processing systems","author":"Shrestha","year":"2018"},{"issue":"1","key":"2022042221321272100_B31","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"2022042221321272100_B32","doi-asserted-by":"crossref","first-page":"10320","DOI":"10.1609\/aaai.v35i12.17236","article-title":"Training spiking neural networks with accumulated spiking flow.","author":"Wu","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2022042221321272100_B33","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1609\/aaai.v33i01.33011311","article-title":"Direct training for spiking neural networks: Faster, larger, better.","author":"Wu","year":"2019","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2022042221321272100_B34","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":"2022042221321272100_B35","author":"Xiao","year":"2017","journal-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms"},{"key":"2022042221321272100_B36","author":"Zhang","year":"2020","journal-title":"Temporal spike sequence learning via backpropagation for deep spiking neural networks"},{"key":"2022042221321272100_B37","first-page":"2921","article-title":"Learning deep features for discriminative localization.","author":"Zhou","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/34\/5\/1170\/2008673\/neco_a_01480.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/34\/5\/1170\/2008673\/neco_a_01480.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T05:23:42Z","timestamp":1674883422000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/34\/5\/1170\/109666\/Training-Deep-Convolutional-Spiking-Neural"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,15]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,4,15]]},"published-print":{"date-parts":[[2022,4,15]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01480","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,5]]},"published":{"date-parts":[[2022,4,15]]}}}