{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:06:02Z","timestamp":1773119162125,"version":"3.50.1"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007940","name":"Urumqi Science and Technology Bureau","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007940","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010880","name":"State Grid Corporation of China","doi-asserted-by":"publisher","award":["5700-202358838A-4-3-WL"],"award-info":[{"award-number":["5700-202358838A-4-3-WL"]}],"id":[{"id":"10.13039\/501100010880","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.neunet.2025.108350","type":"journal-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T23:38:19Z","timestamp":1763854699000},"page":"108350","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Towards efficient and accurate spiking neural networks via adaptive bit allocation"],"prefix":"10.1016","volume":"196","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1872-1170","authenticated-orcid":false,"given":"Yao","family":"Xingting","sequence":"first","affiliation":[]},{"given":"Hu","family":"Qinghao","sequence":"additional","affiliation":[]},{"given":"Zhou","family":"Fei","sequence":"additional","affiliation":[]},{"given":"Liu","family":"Tielong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7835-4739","authenticated-orcid":false,"given":"Li","family":"Gang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6384-0280","authenticated-orcid":false,"given":"Wang","family":"Peisong","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Jian","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.neunet.2025.108350_bib0001","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1109\/TCAD.2015.2474396","article-title":"Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip","volume":"34","author":"Akopyan","year":"2015","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0002","series-title":"Proceedings of the 50th annual IEEE\/ACM international symposium on microarchitecture","first-page":"382","article-title":"Bit-pragmatic deep neural network computing","author":"Albericio","year":"2017"},{"key":"10.1016\/j.neunet.2025.108350_bib0003","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7243","article-title":"A low power, fully event-based gesture recognition system","author":"Amir","year":"2017"},{"key":"10.1016\/j.neunet.2025.108350_bib0004","unstructured":"Bengio, Y., L\u00e9onard, N., & Courville, A. (2013). Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432."},{"key":"10.1016\/j.neunet.2025.108350_bib0005","series-title":"Esann","first-page":"419","article-title":"Spikeprop: Backpropagation for networks of spiking neurons","volume":"vol. 48","author":"Bohte","year":"2000"},{"key":"10.1016\/j.neunet.2025.108350_bib0006","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","first-page":"5350","article-title":"Towards mixed-precision quantization of neural networks via constrained optimization","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2025.108350_bib0007","unstructured":"Choi, J., Wang, Z., Venkataramani, S., Chuang, P. I.-J., Srinivasan, V., & Gopalakrishnan, K. (2018). Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085."},{"key":"10.1016\/j.neunet.2025.108350_bib0008","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2021.651141","article-title":"Comparison of artificial and spiking neural networks on digital hardware","volume":"15","author":"Davidson","year":"2021","journal-title":"Frontiers in Neuroscience"},{"key":"10.1016\/j.neunet.2025.108350_bib0009","series-title":"2009 IEEE Conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neunet.2025.108350_bib0010","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":"10.1016\/j.neunet.2025.108350_bib0011","series-title":"International conference on learning representations","article-title":"Temporal efficient training of spiking neural network via gradient re-weighting","author":"Deng","year":"2021"},{"key":"10.1016\/j.neunet.2025.108350_bib0012","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"293","article-title":"Hawq: Hessian aware quantization of neural networks with mixed-precision","author":"Dong","year":"2019"},{"key":"10.1016\/j.neunet.2025.108350_bib0013","series-title":"International conference on learning representations","article-title":"Learned step size quantization","author":"Esser","year":"2020"},{"issue":"40","key":"10.1016\/j.neunet.2025.108350_bib0014","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adi1480","article-title":"Spikingjelly: An open-source machine learning infrastructure platform for spike-based intelligence","volume":"9","author":"Fang","year":"2023","journal-title":"Science Advances"},{"key":"10.1016\/j.neunet.2025.108350_bib0015","first-page":"21056","article-title":"Deep residual learning in spiking neural networks","volume":"34","author":"Fang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0016","doi-asserted-by":"crossref","unstructured":"Feng, L., Liu, Q., Tang, H., Ma, D., & Pan, G. (2022). Multi-level firing with spiking DS-resnet: Enabling better and deeper directly-trained spiking neural networks. arXiv preprint arXiv:2210.06386.","DOI":"10.24963\/ijcai.2022\/343"},{"key":"10.1016\/j.neunet.2025.108350_bib0017","series-title":"Neuronal dynamics: From single neurons to networks and models of cognition","author":"Gerstner","year":"2014"},{"key":"10.1016\/j.neunet.2025.108350_bib0018","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12244","article-title":"Ternary spike: Learning ternary spikes for spiking neural networks","volume":"vol. 38","author":"Guo","year":"2024"},{"key":"10.1016\/j.neunet.2025.108350_bib0019","series-title":"European conference on computer vision","first-page":"52","article-title":"Real spike: Learning real-valued spikes for spiking neural networks","author":"Guo","year":"2022"},{"key":"10.1016\/j.neunet.2025.108350_bib0020","doi-asserted-by":"crossref","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"},{"issue":"2","key":"10.1016\/j.neunet.2025.108350_bib0021","doi-asserted-by":"crossref","first-page":"2353","DOI":"10.1109\/TNNLS.2024.3355393","article-title":"Advancing spiking neural networks toward deep residual learning","volume":"36","author":"Hu","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"8","key":"10.1016\/j.neunet.2025.108350_bib0022","doi-asserted-by":"crossref","first-page":"5200","DOI":"10.1109\/TNNLS.2021.3119238","article-title":"Spiking deep residual networks","volume":"34","author":"Hu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0023","series-title":"International conference on machine learning","first-page":"9295","article-title":"Sdq: Stochastic differentiable quantization with mixed precision","author":"Huang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108350_bib0024","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13132","article-title":"Metamix: Meta-state precision searcher for mixed-precision activation quantization","volume":"vol. 38","author":"Kim","year":"2024"},{"key":"10.1016\/j.neunet.2025.108350_bib0025","unstructured":"Krizhevsky, A., Hinton, G. et al. (2009). Learning multiple layers of features from tiny images."},{"key":"10.1016\/j.neunet.2025.108350_bib0026","doi-asserted-by":"crossref","first-page":"309","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"},{"key":"10.1016\/j.neunet.2025.108350_bib0027","first-page":"238","article-title":"Bit-serial weight pools: Compression and arbitrary precision execution of neural networks on resource constrained processors","volume":"4","author":"Li","year":"2022","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0028","article-title":"Differentiable spike: Rethinking gradient-descent for training spiking neural networks","volume":"34","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0029","unstructured":"Li, Y., & Zeng, Y. Efficient and accurate conversion of spiking neural network with burst spikes."},{"key":"10.1016\/j.neunet.2025.108350_bib0030","doi-asserted-by":"crossref","DOI":"10.3389\/fnins.2021.726582","article-title":"Es-ImageNet: A million event-stream classification dataset for spiking neural networks","volume":"15","author":"Lin","year":"2021","journal-title":"Frontiers in Neuroscience"},{"key":"10.1016\/j.neunet.2025.108350_bib0031","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1692","article-title":"Spikeconverter: An efficient conversion framework zipping the gap between artificial neural networks and spiking neural networks","volume":"vol. 36","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2025.108350_bib0032","series-title":"2023 IEEE\/ACM International conference on computer aided design (ICCAD)","first-page":"1","article-title":"Deepburning-mixq: An open source mixed-precision neural network accelerator design framework for FPGAs","author":"Luo","year":"2023"},{"issue":"9","key":"10.1016\/j.neunet.2025.108350_bib0033","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"},{"key":"10.1016\/j.neunet.2025.108350_bib0034","series-title":"2024 IEEE International symposium on high-performance computer architecture (HPCA)","first-page":"172","article-title":"Stellar: Energy-efficient and low-latency SNN algorithm and hardware co-design with spatiotemporal computation","author":"Mao","year":"2024"},{"key":"10.1016\/j.neunet.2025.108350_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12444","article-title":"Training high-performance low-latency spiking neural networks by differentiation on spike representation","author":"Meng","year":"2022"},{"key":"10.1016\/j.neunet.2025.108350_bib0036","series-title":"Computer arithmetic","volume":"vol. 20","author":"Parhami","year":"1999"},{"key":"10.1016\/j.neunet.2025.108350_bib0037","unstructured":"Rathi, N., Srinivasan, G., Panda, P., & Roy, K. (2020). Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation. arXiv preprint arXiv:2005.01807."},{"issue":"6088","key":"10.1016\/j.neunet.2025.108350_bib0038","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2025.108350_bib0039","doi-asserted-by":"crossref","first-page":"95","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":"10.1016\/j.neunet.2025.108350_bib0040","series-title":"Proceedings of the 46th international symposium on computer architecture","first-page":"304","article-title":"Laconic deep learning inference acceleration","author":"Sharify","year":"2019"},{"key":"10.1016\/j.neunet.2025.108350_bib0041","series-title":"Proceedings of the 55th annual design automation conference","first-page":"1","article-title":"Loom: Exploiting weight and activation precisions to accelerate convolutional neural networks","author":"Sharify","year":"2018"},{"key":"10.1016\/j.neunet.2025.108350_bib0042","series-title":"2018 ACM\/IEEE 45Th annual international symposium on computer architecture (ISCA)","first-page":"764","article-title":"Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network","author":"Sharma","year":"2018"},{"key":"10.1016\/j.neunet.2025.108350_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"27538","article-title":"Are conventional SNNs really efficient? a perspective from network quantization","author":"Shen","year":"2024"},{"key":"10.1016\/j.neunet.2025.108350_bib0044","unstructured":"Tahmasebi, F., Wang, Y., Huang, B. Y. H., & Kwon, H. (2024). Flexibit: Fully flexible precision bit-parallel accelerator architecture for arbitrary mixed precision ai. arXiv preprint arXiv:2411.18065."},{"key":"10.1016\/j.neunet.2025.108350_bib0045","unstructured":"Uhlich, S., Mauch, L., Cardinaux, F., Yoshiyama, K., Garcia, J. A., Tiedemann, S., Kemp, T., & Nakamura, A. (2019). Mixed precision dnns: All you need is a good parametrization. arXiv preprint arXiv:1905.11452."},{"key":"10.1016\/j.neunet.2025.108350_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8612","article-title":"Haq: Hardware-aware automated quantization with mixed precision","author":"Wang","year":"2019"},{"key":"10.1016\/j.neunet.2025.108350_bib0047","unstructured":"Wu, B., Wang, Y., Zhang, P., Tian, Y., Vajda, P., & Keutzer, K. (2018a). Mixed precision quantization of convnets via differentiable neural architecture search. arXiv preprint arXiv:1812.00090."},{"key":"10.1016\/j.neunet.2025.108350_bib0048","doi-asserted-by":"crossref","first-page":"331","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":"10.1016\/j.neunet.2025.108350_bib0049","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1311","article-title":"Direct training for spiking neural networks: Faster, larger, better","volume":"vol. 33","author":"Wu","year":"2019"},{"issue":"11","key":"10.1016\/j.neunet.2025.108350_bib0050","doi-asserted-by":"crossref","first-page":"6249","DOI":"10.1109\/TNNLS.2021.3073016","article-title":"Liaf-net: Leaky integrate and analog fire network for lightweight and efficient spatiotemporal information processing","volume":"33","author":"Wu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0051","unstructured":"Xiao, Y., Tian, X., Ding, Y., Ding, P., Jing, M., & Zuo, L. (2024). Multi-bit mechanism: A novel information transmission paradigm for spiking neural networks. arxiv preprint arxiv:2407.05739."},{"key":"10.1016\/j.neunet.2025.108350_bib0052","unstructured":"Xing, X., Gao, B., Zhang, Z., Clifton, D. A., Xiao, S., Du, L., Li, G., & Zhang, J. (2024a). SpikeLLM: Scaling up spiking neural network to large language models via saliency-based spiking. arXiv preprint arXiv:2407.04752."},{"key":"10.1016\/j.neunet.2025.108350_bib0053","unstructured":"Xing, X., Zhang, Z., Ni, Z., Xiao, S., Ju, Y., Fan, S., Wang, Y., Zhang, J., & Li, G. (2024b). SpikeLM: Towards general spike-driven language modeling via elastic bi-spiking mechanisms. arXiv preprint arXiv:2406.03287."},{"key":"10.1016\/j.neunet.2025.108350_bib0054","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"10221","article-title":"Temporal-wise attention spiking neural networks for event streams classification","author":"Yao","year":"2021"},{"issue":"8","key":"10.1016\/j.neunet.2025.108350_bib0055","doi-asserted-by":"crossref","first-page":"9393","DOI":"10.1109\/TPAMI.2023.3241201","article-title":"Attention spiking neural networks","volume":"45","author":"Yao","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108350_bib0056","first-page":"32160","article-title":"Glif: A unified gated leaky integrate-and-fire neuron for spiking neural networks","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108350_bib0057","unstructured":"Zhang, Y., Wang, M., Zou, L., Liu, W., Zhen, H.-L., Yuan, M., & Yu, B. (2024). Mixpe: Quantization and hardware co-design for efficient llm inference. arXiv preprint arXiv:2411.16158."},{"key":"10.1016\/j.neunet.2025.108350_bib0058","series-title":"International conference on machine learning","first-page":"12546","article-title":"Differentiable dynamic quantization with mixed precision and adaptive resolution","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2025.108350_bib0059","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11062","article-title":"Going deeper with directly-trained larger spiking neural networks","volume":"vol. 35","author":"Zheng","year":"2021"},{"key":"10.1016\/j.neunet.2025.108350_bib0060","unstructured":"Zhou, Z., Zhu, Y., He, C., Wang, Y., Yan, S., Tian, Y., & Yuan, L. (2022). Spikformer: When spiking neural network meets transformer. arXiv preprint arXiv:2209.15425."},{"key":"10.1016\/j.neunet.2025.108350_bib0061","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4923","article-title":"Binary ensemble neural network: More bits per network or more networks per bit?","author":"Zhu","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025012316?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025012316?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T16:53:53Z","timestamp":1773075233000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025012316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":61,"alternative-id":["S0893608025012316"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108350","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards efficient and accurate spiking neural networks via adaptive bit allocation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108350","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108350"}}