{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:52:23Z","timestamp":1760057543476,"version":"build-2065373602"},"reference-count":28,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T00:00:00Z","timestamp":1739491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Recovery and Resilience Plan (NRRP)","award":["PE0000021","F53C22000770007"],"award-info":[{"award-number":["PE0000021","F53C22000770007"]}]},{"name":"European Union\u2013NextGenerationEU","award":["PE0000021","F53C22000770007"],"award-info":[{"award-number":["PE0000021","F53C22000770007"]}]},{"name":"Ministero dell\u2019Universit\u00e0 e della Ricerca (MUR)","award":["PE0000021","F53C22000770007"],"award-info":[{"award-number":["PE0000021","F53C22000770007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>In this paper, a new algorithm for the training of Locally Recurrent Neural Networks (LRNNs) is presented, which aims to reduce computational complexity and at the same time guarantee the stability of the network during the training. The main feature of the proposed algorithm is the capability to represent the gradient of the error in an explicit form. The algorithm builds on the interpretation of Fibonacci\u2019s sequence as the output of an IIR second-order filter, which makes it possible to use Binet\u2019s formula that allows the generic terms of the sequence to be calculated directly. Thanks to this approach, the gradient of the loss function during the training can be explicitly calculated, and it can be expressed in terms of the parameters, which control the stability of the neural network.<\/jats:p>","DOI":"10.3390\/a18020104","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T04:48:51Z","timestamp":1739508531000},"page":"104","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Training Algorithm for Locally Recurrent Neural Networks Based on the Explicit Gradient of the Loss Function"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0270-6432","authenticated-orcid":false,"given":"Sara","family":"Carcangiu","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Cagliari, 09124 Cagliari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0008-2985","authenticated-orcid":false,"given":"Augusto","family":"Montisci","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Cagliari, 09124 Cagliari, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","article-title":"Dynamic Neural Networks: A Survey","volume":"44","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1162\/neco.1989.1.1.39","article-title":"Modular Construction of Time-Delay Neural Networks for Speech Recognition","volume":"1","author":"Waibel","year":"1989","journal-title":"Neural Comput."},{"key":"ref_3","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4ckinger, E., and Shah, R. (December, January 29). Signature Verification using a \u201cSiamese\u201d Time Delay Neural Network. Proceedings of the Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/TCSI.2004.841574","article-title":"Global asymptotic and robust stability of recurrent neural networks with time delays","volume":"52","author":"Cao","year":"2005","journal-title":"IEEE Trans. Circuits Syst. Regul. Pap."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.neunet.2017.03.002","article-title":"A time-delay neural network for solving time-dependent shortest path problem","volume":"90","author":"Huang","year":"2017","journal-title":"Neural Netw."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1162\/neco.1993.5.2.165","article-title":"Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms","volume":"5","author":"Nerrand","year":"1993","journal-title":"Neural Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Htike, K.K., and Khalifa, O.O. (2010, January 11\u201312). Rainfall forecasting models using focused time-delay neural networks. Proceedings of the International Conference on Computer and Communication Engineering (ICCCE\u201910), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICCCE.2010.5556806"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/0893-6080(88)90021-4","article-title":"Nonlinear neural networks: Principles, mechanisms, and architectures","volume":"1","author":"Grossberg","year":"1988","journal-title":"Neural Netw."},{"key":"ref_9","unstructured":"Haykin, S.S. (2002). Adaptive Filter Theory, Pearson Education."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1109\/PROC.1975.10036","article-title":"Adaptive noise cancelling: Principles and applications","volume":"63","author":"Widrow","year":"1975","journal-title":"Proc. IEEE"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1109\/TMTT.2005.845723","article-title":"A comparative overview of microwave and wireless power-amplifier behavioral modeling approaches","volume":"53","author":"Pedro","year":"2005","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1038\/s42254-023-00595-y","article-title":"A new frontier for Hopfield networks","volume":"5","author":"Krotov","year":"2023","journal-title":"Nat. Rev. Phys."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/S0166-4115(97)80111-2","article-title":"Chapter 25\u2014Serial Order: A Parallel Distributed Processing Approach","volume":"Volume 121","author":"Donahoe","year":"1997","journal-title":"Advances in Psychology"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding Structure in Time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1162\/neco.1991.3.3.375","article-title":"FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling","volume":"3","author":"Back","year":"1991","journal-title":"Neural Comput."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Giles, C.L., and Gori, M. (1998). Recurrent neural network architectures: An overview. Adaptive Processing of Sequences and Data Structures: International Summer School on Neural Networks \u201cE.R. Caianiello\u201d Vietri sul Mare, Tutorial Lectures, Salerno, Italy, 6\u201313 September 1997, Springer.","DOI":"10.1007\/BFb0053992"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1109\/82.861421","article-title":"Intrinsic stability-control method for recursive filters and neural networks","volume":"47","author":"Campolucci","year":"2000","journal-title":"IEEE Trans. Circuits Syst. II Analog Digit. Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/5.58337","article-title":"Backpropagation through time: What it does and how to do it","volume":"78","author":"Werbos","year":"1990","journal-title":"Proc. IEEE"},{"key":"ref_19","unstructured":"Campolucci, P., Uncini, A., and Piazza, F. (1996, January 12). Causal back propagation through time for locally recurrent neural networks. Proceedings of the 1996 IEEE International Symposium on Circuits and Systems, Circuits and Systems Connecting the World, ISCAS 96, Atlanta, GA, USA."},{"key":"ref_20","unstructured":"Campolucci, P., Uncini, A., and Piazza, F. (1996, January 9). Fast adaptive IIR-MLP neural networks for signal processing applications. Proceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, Atlanta, GA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Montisci, A. (2023). A free from local minima algorithm for training regressive MLP neural networks. arXiv.","DOI":"10.54364\/AAIML.2024.41120"},{"key":"ref_22","unstructured":"Carini, A., Mathews, V.J., and Sicuranza, G.L. (1997, January 21\u201324). Sufficient stability bounds for slowly varying discrete-time recursive linear filters. Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, Munich, Germany."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1162\/neco.1992.4.2.141","article-title":"First- and Second-Order Methods for Learning: Between Steepest Descent and Newton\u2019s Method","volume":"4","author":"Battiti","year":"1992","journal-title":"Neural Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1515\/zna-1980-0308","article-title":"Irregular Oscillations in a Realistic Abstract Quadratic Mass Action System","volume":"35","author":"Willamowski","year":"1980","journal-title":"Z. F\u00fcr Naturforschung A"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Niu, H., Wang, H., and Zhang, Q. (2010, January 29\u201331). The Chaos Anti-control in the Willamowski-R\u00f6ssler Reaction. Proceedings of the 2010 International Workshop on Chaos-Fractal Theories and Applications, Kunming, China.","DOI":"10.1109\/IWCFTA.2010.60"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"4281219","DOI":"10.1155\/2020\/4281219","article-title":"Forecasting-Aided Monitoring for the Distribution System State Estimation","volume":"2020","author":"Carcangiu","year":"2020","journal-title":"Complexity"},{"key":"ref_27","unstructured":"(2025, February 04). Irish Social Science Data Archive. Home, Irish Social Science Data Archive. Irish Social Science Data Archive. Available online: https:\/\/www.ucd.ie\/issda\/data\/commissionforenergyregulationcer\/."},{"key":"ref_28","unstructured":"Martin, G. (2011). Electricity Smart Metering Customer Behaviour Trials Findings Report, CER Commission for Energy Regulation. Technical Report."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/2\/104\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:34:14Z","timestamp":1760027654000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/2\/104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":28,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["a18020104"],"URL":"https:\/\/doi.org\/10.3390\/a18020104","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,2,14]]}}}