{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:35:46Z","timestamp":1760146546840,"version":"build-2065373602"},"reference-count":22,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T00:00:00Z","timestamp":1731715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Brain Sciences"],"abstract":"<jats:p>Background: To investigate the behavior of spiking neural networks (SNNs), the sensitivity of input perturbation serves as an effective metric for assessing the influence on the network output. However, existing methods fall short in evaluating the sensitivity of SNNs featuring biologically plausible leaky integrate-and-fire (LIF) neurons due to the intricate neuronal dynamics during the feedforward process. Methods: This paper first defines the sensitivity of a temporal-coded spiking neuron (SN) as the deviation between the perturbed and unperturbed output under a given input perturbation with respect to overall inputs. Then, the sensitivity algorithm of an entire SNN is derived iteratively from the sensitivity of each individual neuron. Instead of using the actual firing time, the desired firing time is employed to derive a more precise analytical expression of the sensitivity. Moreover, the expectation of the membrane potential difference is utilized to quantify the magnitude of the input deviation. Results\/Conclusions: The theoretical results achieved with the proposed algorithm are in reasonable agreement with the simulation results obtained with extensive input data. The sensitivity also varies monotonically with changes in other parameters, except for the number of time steps, providing valuable insights for choosing appropriate values to construct the network. Nevertheless, the sensitivity exhibits a piecewise decreasing tendency with respect to the number of time steps, with the length and starting point of each piece contingent upon the specific parameter values of the neuron.<\/jats:p>","DOI":"10.3390\/brainsci14111149","type":"journal-article","created":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T04:07:09Z","timestamp":1731902829000},"page":"1149","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sensitivity of Spiking Neural Networks Due to Input Perturbation"],"prefix":"10.3390","volume":"14","author":[{"given":"Haoran","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqin","family":"Zeng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3701-3185","authenticated-orcid":false,"given":"Yang","family":"Zou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1038\/376021a0","article-title":"Time for a New Neural Code?","volume":"376","author":"Sejnowski","year":"1995","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1162\/08997660152002852","article-title":"Rate Coding versus Temporal Order Coding: What the Retinal Ganglion Cells Tell the Visual Cortex","volume":"13","author":"Rullen","year":"2001","journal-title":"Neural Comput."},{"key":"ref_3","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 Netw."},{"key":"ref_4","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_5","doi-asserted-by":"crossref","unstructured":"Yang, S., Linares-Barranco, B., and Chen, B. (2022). Heterogeneous Ensemble-Based Spike-Driven Few-Shot Online Learning. Front. Neurosci., 16.","DOI":"10.3389\/fnins.2022.850932"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sengupta, A., Ye, Y., Wang, R., Liu, C., and Roy, K. (2019). Going Deeper in Spiking Neural Networks: VGG and Residual Architectures. Front. Neurosci., 13.","DOI":"10.3389\/fnins.2019.00095"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","article-title":"Deep Learning in Spiking Neural Networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Netw."},{"key":"ref_8","doi-asserted-by":"crossref","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":"ref_9","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_10","doi-asserted-by":"crossref","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":"Int. J. Comput. Vis."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1109\/TNN.2007.894058","article-title":"Localized Generalization Error Model and Its Application to Architecture Selection for Radial Basis Function Neural Network","volume":"18","author":"Yeung","year":"2007","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.patcog.2006.07.002","article-title":"Image Classification with the Use of Radial Basis Function Neural Networks and the Minimization of the Localized Generalization Error","volume":"40","author":"Ng","year":"2007","journal-title":"Pattern Recognitio"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1109\/72.963772","article-title":"Sensitivity Analysis of Multilayer Perceptron to Input and Weight Perturbations","volume":"12","author":"Zeng","year":"2001","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/72.977266","article-title":"Using Function Approximation to Analyze the Sensitivity of MLP with Antisymmetric Squashing Activation Function","volume":"13","author":"Yeung","year":"2002","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1109\/TNN.2010.2077681","article-title":"Computing and Analyzing the Sensitivity of MLP Due to the Errors of the i.i.d. Inputs and Weights Based on CLT","volume":"21","author":"Yang","year":"2010","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1016\/j.neucom.2005.04.010","article-title":"Hidden Neuron Pruning of Multilayer Perceptrons Using a Quantified Sensitivity Measure","volume":"69","author":"Zeng","year":"2006","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1109\/TNNLS.2013.2246578","article-title":"Effective Neural Network Ensemble Approach for Improving Generalization Performance","volume":"24","author":"Yang","year":"2013","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.neucom.2016.10.060","article-title":"A Neural Network Sensitivity Analysis in the Presence of Random Fluctuations","volume":"224","author":"Kapanova","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.neucom.2016.09.044","article-title":"Supervised Learning in Spiking, Neural Networks with Noise-Threshold","volume":"219","author":"Zhang","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lee, C., Sarwar, S.S., Panda, P., Srinivasan, G., and Roy, K. (2020). Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures. Front. Neurosci., 14.","DOI":"10.3389\/fnins.2020.00119"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6178","DOI":"10.1109\/TNNLS.2018.2826721","article-title":"First-Spike-Based Visual Categorization Using Reward-Modulated STDP","volume":"29","author":"Mozafari","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.neunet.2017.12.005","article-title":"STDP-Based Spiking Deep Convolutional Neural Networks for Object Recognition","volume":"99","author":"Kheradpisheh","year":"2018","journal-title":"Neural Netw."}],"container-title":["Brain Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3425\/14\/11\/1149\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:33:48Z","timestamp":1760114028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3425\/14\/11\/1149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,16]]},"references-count":22,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["brainsci14111149"],"URL":"https:\/\/doi.org\/10.3390\/brainsci14111149","relation":{},"ISSN":["2076-3425"],"issn-type":[{"type":"electronic","value":"2076-3425"}],"subject":[],"published":{"date-parts":[[2024,11,16]]}}}