Circuit design and exponential stabilization of memristive neural networks
Open accessAbstract
This paper addresses the problem of circuit design and global exponential stabilization of memristive neural networks with time-varying delays and general activation functions. Based on the Lyapunov-Krasovskii functional method and free weighting matrix technique, a delay-dependent criteria for the global exponential stability and stabilization of memristive neural networks are derived in form of linear matrix inequalities (LMIs). Two numerical examples are elaborated to illustrate the characteristics of the results. It is noteworthy that the traditional assumptions on the boundness of the derivative of the time-varying delays are removed.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Actual memristive elements are two-terminal resistive devices with memory defined by Eqs. (3) and (4) in the voltage-controlled case.
“To proceed, let us first recall the definition of actual memristive elements [63]. These are two-terminal resistive devices with memory defined (in the voltage-controlled case [63]) by”
From On the validity of memristor modeling in the neural network literature (2020) · cites this paper as [63]
Section 2.1 (page unavailable) models a memristor through voltage-dependent memductance that switches according to recent behavior, supporting the resistive-memory aspect. It does not define actual memristive elements as two-terminal devices or give a general voltage-controlled device definition; its equations concern a neural-network circuit. (LLM, conf=0.81)
Experimental — accuracy not yet measuredWhen subjected to time-dependent input, memristive elements typically exhibit pinched hysteresis loops.
“When subjected to time-dependent input, memristive elements typically exhibit pinched hysteresis loops.”
From On the validity of memristor modeling in the neural network literature (2020) · cites this paper as [63]
The Introduction discusses time-varying delays in memristive neural networks, not the response of memristive elements to time-dependent input. Searches for “pinched hysteresis loops,” “hysteresis,” and current–voltage behavior found no passage in our copy addressing the claimed loops. (LLM, conf=0.72)
Experimental — accuracy not yet measuredDue to the presence of memory, pinched hysteresis loops of memristive elements must be strongly dependent on input frequency and voltage amplitude.
“Importantly, due to the presence of memory, these loops must be strongly dependent on the input frequency (and voltage amplitude) [63, 64].”
From On the validity of memristor modeling in the neural network literature (2020) · cites this paper as [63]
The Introduction discusses memristive neural networks and their stability, while the numerical examples examine network behavior. Searches for pinched hysteresis loops and their dependence on input frequency or voltage amplitude found no passage addressing that claim in our copy. (LLM, conf=0.72)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Strukov, D. B., Snider, G. S., Stewart, D. R., & Williams, R. S. (2008) · Nature · doi:10.1038/nature06932 · Cited by 11,744 · see citing works
Memristor—The Missing Circuit Element
Chua, L. (1971) · IEEE Transactions on Circuit Theory · doi:10.1109/tct.1971.1083337 · Cited by 10,268 · cited 2× · see citing works
“Since the experimental prototyping of the memristor (Chua, 1971) was announced by the HP Lab (Strukov, Snider, Stewart, & Williams, 2008), memristive neural networks (MNNs) have been widely investigated, for their immense potential applications in different areas such as brain emulation,…”
BackgroundMethodAn integral inequality in the stability problem of time-delay systems
Gu, K. (2002) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc.2000.914233 · Cited by 1,546 · see citing works
Liu, Y., Wang, Z., & Liu, X. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.03.015 · Cited by 693 · see citing works
Zhang, H., Ma, T., Huang, G.-B., & Wang, Z. (2009) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2009.2030506 · Cited by 391 · see citing works
Synchronization control of a class of memristor-based recurrent neural networks
Wu, A., Wen, S., & Zeng, Z. (2012) · Information Sciences · doi:10.1016/j.ins.2011.07.044 · Cited by 384 · see citing works
Self-citationGlobal Synchronization in an Array of Delayed Neural Networks With Hybrid Coupling
Cao, J., Chen, G., & Li, P. (2008) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2007.914705 · Cited by 346 · see citing works
Self-citationStabilization of Networked Control Systems With a Logic ZOH
Xiong, J., & Lam, J. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2008319 · Cited by 336 · see citing works
Huang, T., Li, C., Duan, S., & Starzyk, J. A. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2192135 · Cited by 329 · see citing works
Self-citationExponential Stabilization of Memristive Neural Networks With Time Delays
Wu, A., & Zeng, Z. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2219554 · Cited by 295 · see citing works
Self-citationWen, S., Zeng, Z., Huang, T., et al. (2014) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2013.2294855 · Cited by 289 · see citing works
Self-citationCellular Neural Networks and Visual Computing: Foundations and Applications
Chua, L. O., & Roska, T. (2002) · Cited by 268 · see citing works
Liu, Q., & Wang, J. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2244908 · Cited by 249 · see citing works
Yue, D., Tian, E., Zhang, Y., et al. (2008) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.2007496 · Cited by 232 · see citing works
Liu, D., Wang, D., Zhao, D., Wei, Q., & Jin, N. (2012) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2012.2198057 · Cited by 222 · see citing works
Robust stability analysis of generalized neural networks with discrete and distributed time delays
Wang, Z., Shu, H., Liu, Y., et al. (2005) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2005.08.166 · Cited by 211 · see citing works
Delay-dependent robust stability criteria for uncertain systems with interval time-varying delay
Peng, C., & Tian, Y. (2007) · Journal of Computational and Applied Mathematics · doi:10.1016/j.cam.2007.03.009 · Cited by 208 · see citing works
Global uniform asymptotic stability of memristor-based recurrent neural networks with time delays
Hu, J., & Wang, J. (2010) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2010.5596359 · Cited by 208 · see citing works
Wu, L., Feng, Z., & Lam, J. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2271046 · Cited by 197 · see citing works
Guo, Z., Wang, J., & Yan, Z. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.08.002 · Cited by 191 · see citing works
Wen, S., Bao, G., Zeng, Z., et al. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.10.001 · Cited by 189 · see citing works
Self-citationLiang, J., Wang, Z., Liu, Y., et al. (2008) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.925724 · Cited by 183 · see citing works
Attractivity Analysis of Memristor-Based Cellular Neural Networks With Time-Varying Delays
Guo, Z., Wang, J., & Yan, Z. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2280556 · Cited by 181 · see citing works
Zeng, H., He, Y. M., Wu, M., et al. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2011.2111383 · Cited by 159 · see citing works
Discrete-time recurrent neural networks with time-varying delays: Exponential stability analysis
Liu, Y., Wang, Z., Serrano, A., et al. (2006) · Physics Letters A · doi:10.1016/j.physleta.2006.10.073 · Cited by 149 · see citing works
A Recurrent Neural Network for Solving Bilevel Linear Programming Problem
He, X., Li, C., Huang, T., et al. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2280905 · Cited by 127 · see citing works
Self-citationOn global exponential stability of generalized stochastic neural networks with mixed time-delays
Liu, Y., Wang, Z., & Liu, X. (2006) · Neurocomputing · doi:10.1016/j.neucom.2006.01.031 · Cited by 117 · see citing works
Li, X., Gao, H., & Yu, X. (2011) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2011.2125950 · Cited by 102 · see citing works
Phat, V. N., & Trinh, H. M. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2049118 · Cited by 99 · see citing works
Passivity analysis of memristor-based recurrent neural networks with time-varying delays
Wen, S., Zeng, Z., Huang, T., et al. (2013) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2013.05.026 · Cited by 87 · see citing works
Self-citationLuo, B., & Wu, H. (2012) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2012.2194781 · Cited by 82 · see citing works
A One-Layer Recurrent Neural Network for Real-Time Portfolio Optimization With Probability Criterion
Liu, Q., Dang, C., & Huang, T. (2012) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2012.2198812 · Cited by 71 · see citing works
Self-citationDynamic behaviors of memristor-based delayed recurrent networks
Wen, S., Zeng, Z., & Huang, T. (2012) · Neural Computing and Applications · doi:10.1007/s00521-012-0998-y · Cited by 63 · see citing works
Self-citationGlobal exponential stability of a class of memristive neural networks with time-varying delays
Wang, X., Li, C., Huang, T., & Duan, S. (2013) · Neural Computing and Applications · doi:10.1007/s00521-013-1383-1 · Cited by 51 · see citing works
Self-citationCodimension two bifurcation in a delayed neural network with unidirectional coupling
He, X., Li, C., Li, C., et al. (2012) · Nonlinear Analysis Real World Applications · doi:10.1016/j.nonrwa.2012.09.010 · Cited by 41 · see citing works
Memristor crossbar-based unsupervised image learning
Chen, L., Li, C., Huang, T., Chen, Y., & Wang, X. (2013) · Neural Computing and Applications · doi:10.1007/s00521-013-1501-0 · Cited by 39 · see citing works
Self-citationNovel Exponential Stability Criteria of High-Order Neural Networks With Time-Varying Delays
Zheng, C., Zhang, H., & Wang, Z. D. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2010.2059010 · Cited by 37 · see citing works
Noise cancellation of memristive neural networks
Wen, S., Zeng, Z., Huang, T., & Yu, X. (2014) · Neural Networks · doi:10.1016/j.neunet.2014.07.014 · Cited by 29 · see citing works
Self-citationHarmless delays for global exponential stability of Cohen–Grossberg neural networks
Zhao, W., & Tan, Y. K. (2006) · Mathematics and Computers in Simulation · doi:10.1016/j.matcom.2006.08.003 · Cited by 13 · see citing works
Wang, L., Zhang, R., Xu, Z., et al. (2009) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.2009225 · Cited by 12 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- Chen, G., & Dong, X. (1998). From chaos to order: methodolgies, perspectives, and applications. Singapore: World Scientific.
Cited by
Sorted by citations
On the validity of memristor modeling in the neural network literature
Pershin, Y. V., & Di Ventra, M. (2020) · Neural Networks · doi:10.1016/j.neunet.2019.08.026 · Cited by 49 · see citing works
“ristive” neural networks (MNNs) published during the last decade [1–60] (note that this list may be incomplete, as”
BackgroundGST-memristor-based online learning neural networks
Xiao, S., Xie, X., Wen, S., Zeng, Z., Huang, T., & Jiang, J. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.08.014 · Cited by 45 · see citing works
Self-citation
- Authors
- Wen, S., Huang, T., Zeng, Z., Chen, Y., & Li, P.
- Affiliations
- Huazhong University of Science and Technology (CN)
- Texas A&M University at Qatar (QA)
- University of Pittsburgh (US)
- Texas A&M University (US)
- Corresponding author
- Huang, Tingwen
- Venue
- Neural Networks
- Publisher
- Elsevier BV
- Published
- 2015-03
- Volume
- 63
- Pages
- 48-56
- ISSN
- 0893-6080 (ISSN-L)
- OpenAlex
- W2061607792
- Cited by
- 178
- References
- 40
- Citations by year
- 2026: 3 · 2024: 7 · 2023: 10 · 2022: 9 · 2021: 5 · 2020: 14 · 2019: 21 · 2018: 20 · 2017: 39 · 2016: 21 · 2015: 27 · 2014: 2
- FWCI
- 34.10
- Type
- journal article
- Language
- en
- Open access
- green
- escholarship.org
- Locations
- Neural Networks (publishedVersion)
- PubMed (publishedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Funders
- Natural Science Foundation of China (61125303, 61403152, 61402218)
- National Basic Research Program of China (973 Program) (2011CB710606)
- Program for Science and Technology in Wuhan of China (2014010101010004)
- Program for Changjiang Scholars and Innovative Research Team in University of China (IRT1245)
- NPRP (4-1162-1-181)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Neural Networks Stability and Synchronization
- Physical Sciences › Engineering › Control and Systems Engineering › Stability and Control of Uncertain Systems
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- memristive neural networks, circuit design, global exponential stability, stabilization, time-varying delays, Lyapunov-Krasovskii functional, free-weighting matrix technique, delay-dependent stability conditions, linear matrix inequalities
- MeSH terms
- Algorithms, Neural Networks, Computer, Nonlinear Dynamics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
