{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:01:40Z","timestamp":1759334500643,"version":"build-2065373602"},"reference-count":38,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural science Foundation of Zhejiang province of China","award":["LY23F040003"],"award-info":[{"award-number":["LY23F040003"]}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Algorithms"],"abstract":"<jats:p>Spiking Neural Networks (SNNs), with their event-driven and energy-efficient characteristics, have shown great promise in processing data from neuromorphic sensors. However, the sparse and non-stationary nature of event-based data poses significant challenges to optimization, particularly when using conventional algorithms such as AdamW, which assume smooth gradient dynamics. To address this limitation, we propose MemristiveAdamW, a novel algorithm that integrates memristor-inspired dynamic adjustment mechanisms into the AdamW framework. This optimization algorithm introduces three biologically motivated modules: (1) a direction-aware modulation mechanism that adapts the update direction based on gradient change trends; (2) a memristive perturbation model that encodes history-sensitive adjustment inspired by the physical characteristics of memristors; and (3) a memory decay strategy that ensures stable convergence by attenuating perturbations over time. Extensive experiments are conducted on two representative event-based datasets, Prophesee NCARS and GEN1, across three SNN architectures: Spiking VGG-11, Spiking MobileNet-64, and Spiking DenseNet-121. Results demonstrate that MemristiveAdamW consistently improves convergence speed, classification accuracy, and training stability compared to standard AdamW, with the most significant gains observed in shallow or lightweight SNNs. These findings suggest that memristor-inspired optimization offers a biologically plausible and computationally effective paradigm for training SNNs on event-driven data.<\/jats:p>","DOI":"10.3390\/a18100618","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:52:46Z","timestamp":1759240366000},"page":"618","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MemristiveAdamW: An Optimization Algorithm for Spiking Neural Networks Incorporating Memristive Effects"],"prefix":"10.3390","volume":"18","author":[{"given":"Fan","family":"Jiang","sequence":"first","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}]},{"given":"Zhiwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}]},{"given":"Zheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}]},{"given":"Jumei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Maritime and Transportation, Ningbo University, Ningbo 315211, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","article-title":"Event-based vision: A survey","volume":"44","author":"Gallego","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","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 J. Solid-State Circuits"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Krishnan, K.S., and Krishnan, K.S. (2022). Benchmarking Conventional Vision Models on Neuromorphic Fall Detection and Action Recognition Dataset. arXiv.","DOI":"10.1109\/CCWC54503.2022.9720737"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1162\/neco_a_01086","article-title":"Superspike: Supervised learning in multilayer spiking neural networks","volume":"30","author":"Zenke","year":"2018","journal-title":"Neural Comput."},{"key":"ref_6","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_7","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_8","unstructured":"Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., and Han, J. (2019). On the variance of the adaptive learning rate and beyond. arXiv."},{"key":"ref_9","unstructured":"Luo, L., Xiong, Y., Liu, Y., and Sun, X. (2019). Adaptive gradient methods with dynamic bound of learning rate. arXiv."},{"key":"ref_10","first-page":"1","article-title":"Lookahead optimizer: K steps forward, 1 step back","volume":"32","author":"Zhang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_11","first-page":"1","article-title":"Adaptive methods for nonconvex optimization","volume":"31","author":"Zaheer","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_12","unstructured":"Ma, J., and Yarats, D. (2018). Quasi-hyperbolic momentum and Adam for deep learning. arXiv."},{"key":"ref_13","unstructured":"Ding, J., Ren, X., Luo, R., and Sun, X. (2019). An adaptive and momental bound method for stochastic learning. arXiv."},{"key":"ref_14","first-page":"41727","article-title":"Automatic clipping: Differentially private deep learning made easier and stronger","volume":"36","author":"Bu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sun, H., Yu, H., Shao, Y., Wang, J., Xing, L., Zhang, L., and Zhao, Q. (2024). An improved Adam\u2019s algorithm for stomach image classification. Algorithms, 17.","DOI":"10.3390\/a17070272"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sun, H., Cui, J., Shao, Y., Yang, J., Xing, L., Zhao, Q., and Zhang, L. (2024). A Gastrointestinal Image Classification Method Based on Improved Adam Algorithm. Mathematics, 12.","DOI":"10.3390\/math12162452"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9508","DOI":"10.1109\/TPAMI.2024.3423382","article-title":"Adan: Adaptive nesterov momentum algorithm for faster optimizing deep models","volume":"46","author":"Xie","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","unstructured":"Kleinsorge, A., Kupper, S., Fauck, A., and Rothe, F. (2023). ELRA: Exponential learning rate adaption gradient descent optimization method. arXiv."},{"key":"ref_19","unstructured":"Reddi, S.J., Kale, S., and Kumar, S. (2019). On the convergence of adam and beyond. arXiv."},{"key":"ref_20","first-page":"18795","article-title":"Adabelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"Zhuang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","first-page":"49205","article-title":"Symbolic discovery of optimization algorithms","volume":"36","author":"Chen","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1038\/nature14441","article-title":"Training and operation of an integrated neuromorphic network based on metal-oxide memristors","volume":"521","author":"Prezioso","year":"2015","journal-title":"Nature"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1038\/nature06932","article-title":"The missing memristor found","volume":"453","author":"Strukov","year":"2008","journal-title":"Nature"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Diehl, P.U., and Cook, M. (2015). Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci., 9.","DOI":"10.3389\/fncom.2015.00099"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1038\/s41928-017-0006-8","article-title":"The future of electronics based on memristive systems","volume":"1","author":"Zidan","year":"2018","journal-title":"Nat. Electron."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/s41563-019-0291-x","article-title":"Memristive crossbar arrays for brain-inspired computing","volume":"18","author":"Xia","year":"2019","journal-title":"Nat. Mater."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"eads5340","DOI":"10.1126\/sciadv.ads5340","article-title":"Topology optimization of random memristors for input-aware dynamic SNN","volume":"11","author":"Wang","year":"2025","journal-title":"Sci. Adv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3635165","article-title":"Towards energy-efficient spiking neural networks: A robust hybrid CMOS-memristive accelerator","volume":"20","author":"Nowshin","year":"2024","journal-title":"ACM J. Emerg. Technol. Comput. Syst."},{"key":"ref_29","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","unstructured":"Tieleman, T., and Hinton, G. (2017, January 6\u201311). Rmsprop: Divide the Gradient by a Running Average of its Recent Magnitude. Coursera: Neural Networks for Machine Learning. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bottou, L. (2010, January 22\u201327). Large-Scale Machine Learning with Stochastic Gradient Descent. Proceedings of the COMPSTAT\u20192010, Paris, France.","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref_32","unstructured":"Zhang, Y., Chen, C., Li, Z., Ding, T., Wu, C., Kingma, D.P., Ye, Y., Luo, Z.-Q., and Sun, R. (2024). Adam-mini: Use fewer learning rates to gain more. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1109\/TCT.1971.1083337","article-title":"Memristor-the missing circuit element","volume":"18","author":"Chua","year":"2003","journal-title":"IEEE Trans. Circuit Theory"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1038\/nnano.2012.240","article-title":"Memristive devices for computing","volume":"8","author":"Yang","year":"2013","journal-title":"Nat. Nanotechnol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2400221","DOI":"10.1002\/aelm.202400221","article-title":"Unraveling the roles of switching and relaxation times in volatile electrochemical memristors to mimic neuromorphic dynamical features","volume":"10","author":"Dutta","year":"2024","journal-title":"Adv. Electron. Mater."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ali, S., Ullah, M.A., Raza, A., Iqbal, M.W., Khan, M.F., Rasheed, M., Ismail, M., and Kim, S. (2023). Recent advances in cerium oxide-based memristors for neuromorphic computing. Nanomaterials, 13.","DOI":"10.3390\/nano13172443"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1600090","DOI":"10.1002\/aelm.201600090","article-title":"Memristors for energy\u2014Efficient new computing paradigms","volume":"2","author":"Jeong","year":"2016","journal-title":"Adv. Electron. Mater."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1109\/LED.2017.2722463","article-title":"Emulating short-term and long-term plasticity of bio-synapse based on Cu\/a-Si\/Pt memristor","volume":"38","author":"Zhang","year":"2017","journal-title":"IEEE Electron Device Lett."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/10\/618\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T16:47:44Z","timestamp":1759250864000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/10\/618"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["a18100618"],"URL":"https:\/\/doi.org\/10.3390\/a18100618","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,9,30]]}}}