{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:22:23Z","timestamp":1753881743810,"version":"3.41.2"},"reference-count":44,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T00:00:00Z","timestamp":1690243200000},"content-version":"vor","delay-in-days":205,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2232021D-26"],"award-info":[{"award-number":["2232021D-26"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Spiking neural networks (SNNs) are highly computationally efficient artificial intelligence methods due to their advantages in having a biologically plausible computational framework. Recent research has shown that SNN trained using backpropagation (SNN\u2010BP) exhibits excellent performance and has shown great potential in tasks such as image classification and security detection. However, the backpropagation method limits the dynamics and biological plausibility of the neural models in SNN, which will limit the recognition and simulation performance of SNN. In order to make neural models more similar to biological neurons, this study proposes a leaky integrate\u2010and\u2010fire (LIF) neuron model with dense intralayer connections, as well as efficient forward and backward processes in BP training. The new model will make the interaction between neurons within the layer more frequent, enhancing the intrinsic information exchange capability of SNN. An effective probabilistic spike\u2010timing dependent plasticity (STDP) method is also proposed to reduce the overweighted connections between neurons, as well as a hybrid training method using BP and probabilistic STDP. The training method combines the advantages of BP and STDP to improve the performance of SNN models. An intralayer\u2010connected SNN with hybrid training (ISNN\u2010HY) is proposed with the combination of these improvements. The proposed model was evaluated on three static image datasets and one neuromorphic dataset. The results showed that the performance of ISNN\u2010HY is superior to that of other SNN\u2010BP models. The proposed method also makes it possible to accurately simulate biological neural systems.<\/jats:p>","DOI":"10.1155\/2023\/3135668","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T18:35:22Z","timestamp":1690310122000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Intralayer\u2010Connected Spiking Neural Network with Hybrid Training Using Backpropagation and Probabilistic Spike\u2010Timing Dependent Plasticity"],"prefix":"10.1155","volume":"2023","author":[{"given":"Long","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuhang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8147-5109","authenticated-orcid":false,"given":"Zijian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,7,25]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/78829"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.3043415"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01086"},{"key":"e_1_2_9_6_2","first-page":"12022","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang W.","year":"2020"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17236"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.012"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.005"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00774"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00331"},{"key":"e_1_2_9_12_2","article-title":"Spike-train level backpropagation for training deep recurrent spiking neural networks","volume":"32","author":"Zhang W.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22772"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"ChengX. YunzheH. XuJ. andXuB. Lisnn: improving spiking neural networks with lateral interactions for robust object recognition Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence (IJCAI) August 2021 Virtual Montreal.","DOI":"10.24963\/ijcai.2020\/211"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"ZhangW.andPengL. Spiking neural networks with laterally-inhibited self-recurrent units Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN) July 2021 IEEE Shenzhen China https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9533726.","DOI":"10.1109\/IJCNN52387.2021.9533726"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01393"},{"key":"e_1_2_9_17_2","unstructured":"ZhangW.andPengL. Composing recurrent spiking neural networks using locally-recurrent motifs and risk-mitigating architectural optimization 2021 https:\/\/arxiv.org\/abs\/2108.01793."},{"key":"e_1_2_9_18_2","unstructured":"TavanaeiA.andMaidaA. S. Bio-inspired spiking convolutional neural network using layer-wise sparse coding and stdp learning 2016 https:\/\/arxiv.org\/abs\/1611.03000."},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"TavanaeiA.andMaidaA. S. Multi-layer unsupervised learning in a spiking convolutional neural network Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN) July 2017 IEEE Anchorage AK USA https:\/\/doi.org\/10.1109\/IJCNN.2017.7966099 2-s2.0-85031035650.","DOI":"10.1109\/IJCNN.2017.7966099"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsii.2021.3137987"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"TavanaeiA. KirbyZ. andMaidaA. S. Training spiking convnets by stdp and gradient descent Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN) July 2018 IEEE Rio de Janeiro Brazil https:\/\/doi.org\/10.1109\/IJCNN.2018.8489104 2-s2.0-85056496352.","DOI":"10.1109\/IJCNN.2018.8489104"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"GuoW. LinX. andYangX. A supervised learning algorithm for recurrent spiking neural networks based on bp-stdp Proceedings of the Neural Information Processing: 28th International Conference ICONIP 2021 December 2021 Sanur Bali Indonesia Springer 583\u2013590.","DOI":"10.1007\/978-3-030-92307-5_68"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.756876"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-020-0277-3"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn.2018.6"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-006-0068-6"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnsyn.2012.00002"},{"key":"e_1_2_9_28_2","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2018.00079"},{"key":"e_1_2_9_29_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.590164"},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_9_31_2","unstructured":"HanX. RasulK. andRolandV. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms 2017 https:\/\/arxiv.org\/abs\/1708.07747."},{"volume-title":"Learning Multiple Layers of Features from Tiny Images","year":"2009","author":"Krizhevsky A.","key":"e_1_2_9_32_2"},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2015.00437"},{"key":"e_1_2_9_34_2","unstructured":"LoshchilovI.andHutterF. Decoupled weight decay regularization Proceedings of the International Conference on Learning Representations May 2018 Vancouver CANADA."},{"key":"e_1_2_9_35_2","doi-asserted-by":"crossref","unstructured":"DattaG. KunduS. andBeerelP. A. Training energy-efficient deep spiking neural networks with single-spike hybrid input encoding Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN) May 2021 IEEE Shenzhen China https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9534306.","DOI":"10.1109\/IJCNN52387.2021.9534306"},{"key":"e_1_2_9_36_2","article-title":"Hybrid macro\/micro level backpropagation for training deep spiking neural networks","volume":"31","author":"Jin Y.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.162"},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011311"},{"key":"e_1_2_9_39_2","unstructured":"RathiN. SrinivasanG. PandaP. andRoyK. Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation 2020 https:\/\/arxiv.org\/abs\/2005.01807."},{"key":"e_1_2_9_40_2","article-title":"Diet-snn: a low-latency spiking neural network with direct input encoding and leakage and threshold optimization","volume":"34","author":"Rathi N.","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_2_9_41_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00095"},{"key":"e_1_2_9_42_2","article-title":"Slayer: spike layer error reassignment in time","volume":"31","author":"Sumit B. S.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10322-8"},{"key":"e_1_2_9_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2016.2636291"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3135668.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/3135668.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/3135668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:19:15Z","timestamp":1735622355000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/3135668"}},"subtitle":[],"editor":[{"given":"Alexander","family":"Ho\u0161ovsk\u00fd","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/3135668"],"URL":"https:\/\/doi.org\/10.1155\/2023\/3135668","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"type":"print","value":"0884-8173"},{"type":"electronic","value":"1098-111X"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-11-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3135668"}}