{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:18:12Z","timestamp":1767140292319,"version":"build-2238731810"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"34","license":[{"start":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T00:00:00Z","timestamp":1719878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T00:00:00Z","timestamp":1719878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Recurrent neural networks (RNN) are ubiquitous computing systems for sequences and multivariate time-series data. While several robust RNN architectures are known, it is unclear how to relate RNN initialization, architecture, and other hyperparameters with accuracy for a given task. In this work, we propose treating RNN as dynamical systems and correlating hyperparameters with accuracy through Lyapunov spectral analysis, a methodology designed explicitly for nonlinear dynamical systems. To address the fact that RNN features go beyond the existing Lyapunov spectral analysis, we propose to infer relevant features from the Lyapunov spectrum with an Autoencoder and an embedding of its Latent representation (AeLLE). Our studies of various RNN architectures show that AeLLE successfully correlates RNN Lyapunov spectrum with accuracy. Furthermore, the Latent representation learned by AeLLE is generalizable to novel inputs from the same task and is formed early in the process of RNN training. The latter property allows for predicting the accuracy to which RNN would converge when training is complete. We conclude that the representation of RNN through the Lyapunov spectrum, along with AeLLE, provides a novel method for the organization and interpretation of variants of RNN architectures.<\/jats:p>","DOI":"10.1007\/s00521-024-09824-6","type":"journal-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T04:03:28Z","timestamp":1719893008000},"page":"21211-21226","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Lyapunov-guided representation of recurrent neural network performance"],"prefix":"10.1007","volume":"36","author":[{"given":"Ryan","family":"Vogt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3136-4531","authenticated-orcid":false,"given":"Eli","family":"Shlizerman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,2]]},"reference":[{"key":"9824_CR1","doi-asserted-by":"crossref","unstructured":"Pang B, Zha K, Cao H, Shi C, Lu C (2019) Deep RNN framework for visual sequential applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00051"},{"key":"9824_CR2","doi-asserted-by":"crossref","unstructured":"Mikolov T, Karafi\u00e1t M, Burget L, \u010cernock\u1ef3 J, Khudanpur S (2010) Recurrent neural network based language model. In: Eleventh Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2010-343"},{"issue":"5","key":"9824_CR3","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1109\/72.712164","volume":"9","author":"S Das","year":"1998","unstructured":"Das S, Olurotimi O (1998) Noisy recurrent neural networks: the continuous-time case. IEEE Trans Neural Netw 9(5):913\u2013936. https:\/\/doi.org\/10.1109\/72.712164","journal-title":"IEEE Trans Neural Netw"},{"issue":"4","key":"9824_CR4","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/72.935096","volume":"12","author":"P Tino","year":"2001","unstructured":"Tino P, Schittenkopf C, Dorffner G (2001) Financial volatility trading using recurrent neural networks. IEEE Trans Neural Netw 12(4):865\u2013874","journal-title":"IEEE Trans Neural Netw"},{"key":"9824_CR5","doi-asserted-by":"crossref","unstructured":"Su K, Liu X, Shlizerman E(2020) Predict & cluster: unsupervised skeleton based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9631\u2013 9640","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"9824_CR6","unstructured":"Pennington J, Schoenholz S, Ganguli S (2017) Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice. In: Advances in Neural Information Processing Systems, pp 4785\u2013 4795"},{"key":"9824_CR7","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp 3104\u2013 3112"},{"key":"9824_CR8","unstructured":"Gregor K, Danihelka I, Graves A, Rezende D, Wierstra D (2015) Draw: a recurrent neural network for image generation. In: International Conference on Machine Learning, pp 1462\u2013 1471 . PMLR"},{"key":"9824_CR9","unstructured":"Choi K, Fazekas G, Sandler MB (2016) Text-based lstm networks for automatic music composition. CoRR arXiv: abs\/1604.05358"},{"key":"9824_CR10","doi-asserted-by":"crossref","unstructured":"Mao HH, Shin T, Cottrell G (2018) Deepj: Style-specific music generation. In: 2018 IEEE 12th International Conference on Semantic Computing (ICSC), pp 377\u2013 382 . IEEE","DOI":"10.1109\/ICSC.2018.00077"},{"key":"9824_CR11","doi-asserted-by":"crossref","unstructured":"Guo D, Zhou W, Li H, Wang M (2018) Hierarchical LSTM for sign language translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.12235"},{"issue":"8","key":"9824_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"9824_CR13","doi-asserted-by":"crossref","unstructured":"Cho K, Merrienboer B, G\u00fcl\u00e7ehre \u00c7, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. CoRR abs\/1406.1078arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"9824_CR14","unstructured":"Chung J, G\u00fcl\u00e7ehre \u00c7, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR abs\/1412.3555 arXiv: 1412.3555"},{"key":"9824_CR15","unstructured":"Chang B, Chen M, Haber E, Chi EH (2019) AntisymmetricRNN: a dynamical system view on recurrent neural networks. In: International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=ryxepo0cFX"},{"key":"9824_CR16","unstructured":"Vorontsov E, Trabelsi C, Kadoury S, Pal C (2017) On orthogonality and learning recurrent networks with long term dependencies. In: International Conference on Machine Learning, pp 3570\u2013 3578 . PMLR"},{"key":"9824_CR17","unstructured":"Rusch TK, Mishra S (2021) Coupled oscillatory recurrent neural network (coRNN): an accurate and (gradient) stable architecture for learning long time dependencies. In: International Conference on Learning Representations"},{"key":"9824_CR18","unstructured":"Erichson NB, Azencot O, Queiruga A, Hodgkinson L, Mahoney MW (2020) Lipschitz recurrent neural networks. In: International Conference on Learning Representations"},{"issue":"1","key":"9824_CR19","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/BF02684768","volume":"50","author":"D Ruelle","year":"1979","unstructured":"Ruelle D (1979) Ergodic theory of differentiable dynamical systems. Publications Math\u00e9matiques de l\u2019Institut des Hautes \u00c9tudes Scientifiques 50(1):27\u201358","journal-title":"Publications Math\u00e9matiques de l\u2019Institut des Hautes \u00c9tudes Scientifiques"},{"issue":"1","key":"9824_CR20","doi-asserted-by":"publisher","first-page":"1846","DOI":"10.4249\/scholarpedia.1846","volume":"3","author":"V Oseledets","year":"2008","unstructured":"Oseledets V (2008) Oseledets theorem. Scholarpedia 3(1):1846. https:\/\/doi.org\/10.4249\/scholarpedia.1846. (revision #142085)","journal-title":"Scholarpedia"},{"key":"9824_CR21","unstructured":"Engelken R, Wolf F, Abbott LF (2020) Lyapunov spectra of chaotic recurrent neural networks. arXiv preprint arXiv:2006.02427"},{"key":"9824_CR22","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2022.818799","author":"R Vogt","year":"2022","unstructured":"Vogt R, Puelma Touzel M, Shlizerman E, Lajoie G (2022) On Lyapunov exponents for RNNs: understanding information propagation using dynamical systems tools. Front Appl Math Stat. https:\/\/doi.org\/10.3389\/fams.2022.818799","journal-title":"Front Appl Math Stat"},{"key":"9824_CR23","first-page":"11297","volume":"35","author":"J Mikhaeil","year":"2022","unstructured":"Mikhaeil J, Monfared Z, Durstewitz D (2022) On the difficulty of learning chaotic dynamics with rnns. Adv Neural Inform Process Syst 35:11297\u201311312","journal-title":"Adv Neural Inform Process Syst"},{"key":"9824_CR24","first-page":"5219","volume":"35","author":"L Herrmann","year":"2022","unstructured":"Herrmann L, Granz M, Landgraf T (2022) Chaotic dynamics are intrinsic to neural network training with sgd. Adv Neural Inform Process Syst 35:5219\u20135229","journal-title":"Adv Neural Inform Process Syst"},{"key":"9824_CR25","unstructured":"Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp 1310\u2013 1318"},{"key":"9824_CR26","unstructured":"Poole B, Lahiri S, Raghu M, Sohl-Dickstein J, Ganguli S (2016) Exponential expressivity in deep neural networks through transient chaos. In: Advances in Neural Information Processing Systems, pp 3360\u2013 3368"},{"key":"9824_CR27","doi-asserted-by":"crossref","unstructured":"Wang B, Hoai M (2018) Predicting body movement and recognizing actions: an integrated framework for mutual benefits. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp 341\u2013 348 . IEEE","DOI":"10.1109\/FG.2018.00056"},{"key":"9824_CR28","unstructured":"Chen M, Pennington J, Schoenholz S (2018) Dynamical isometry and a mean field theory of RNNs: gating enables signal propagation in recurrent neural networks. In: International Conference on Machine Learning, pp 873\u2013 882 . PMLR"},{"key":"9824_CR29","unstructured":"Yang G (2019) Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation. arXiv preprint arXiv:1902.04760"},{"key":"9824_CR30","unstructured":"Zheng Y, Shlizerman E (2020) R-FORCE: Robust learning for random recurrent neural networks. arXiv preprint arXiv:2003.11660"},{"key":"9824_CR31","doi-asserted-by":"publisher","first-page":"4122","DOI":"10.1038\/s41467-021-24025-8","volume":"12","author":"C Martin","year":"2021","unstructured":"Martin C, Peng T, Mahoney M (2021) Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data. Nat Commun 12:4122. https:\/\/doi.org\/10.1038\/s41467-021-24025-8","journal-title":"Nat Commun"},{"key":"9824_CR32","doi-asserted-by":"publisher","unstructured":"Naiman I, Azencot O (2021) A Koopman approach to understanding sequence neural models. arXiv . https:\/\/doi.org\/10.48550\/ARXIV.2102.07824","DOI":"10.48550\/ARXIV.2102.07824"},{"key":"9824_CR33","first-page":"4880","volume":"29","author":"S Wisdom","year":"2016","unstructured":"Wisdom S, Powers T, Hershey J, Le Roux J, Atlas L (2016) Full-capacity unitary recurrent neural networks. Adv Neural Inform Process Syst 29:4880\u20134888","journal-title":"Adv Neural Inform Process Syst"},{"key":"9824_CR34","unstructured":"Jing L, Shen Y, Dubcek T, Peurifoy J, Skirlo S, LeCun Y, Tegmark M, Solja\u010di\u0107 M (2017) Tunable efficient unitary neural networks (eUNN) and their application to RNNs. In: International Conference on Machine Learning, pp 1733\u2013 1741 . PMLR"},{"key":"9824_CR35","unstructured":"Mhammedi Z, Hellicar A, Rahman A, Bailey J (2017) Efficient orthogonal parametrisation of recurrent neural networks using householder reflections. In: International Conference on Machine Learning, pp 2401\u2013 2409 . PMLR"},{"key":"9824_CR36","unstructured":"Azencot O, Erichson NB, Ben-Chen M, Mahoney MW (2021) A differential geometry perspective on orthogonal recurrent models. arXiv preprint arXiv:2102.09589"},{"key":"9824_CR37","unstructured":"Kerg G, Goyette K, Puelma\u00a0Touzel M, Gidel G, Vorontsov E, Bengio Y, Lajoie G (2019) Non-normal recurrent neural network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics. Adv Neural Inform Process Syst 32"},{"key":"9824_CR38","first-page":"5124","volume":"34","author":"SH Lim","year":"2021","unstructured":"Lim SH, Erichson NB, Hodgkinson L, Mahoney MW (2021) Noisy recurrent neural networks. Adv Neural Inform Process Syst 34:5124\u20135137","journal-title":"Adv Neural Inform Process Syst"},{"key":"9824_CR39","unstructured":"Maheswaranathan N, Williams A, Golub M, Ganguli S, Sussillo D (2019) Universality and individuality in neural dynamics across large populations of recurrent networks. Adv Neural Inform Process Syst 32"},{"issue":"1","key":"9824_CR40","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1007\/BF01246445","volume":"31","author":"O platform","year":"1930","unstructured":"platform O (1930) The ordinal numbers of systems of linear differential equations. Math J 31(1):748\u2013766","journal-title":"Math J"},{"key":"9824_CR41","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1103\/PhysRevLett.73.1927","volume":"73","author":"S Dawson","year":"1994","unstructured":"Dawson S, Grebogi C, Sauer T, Yorke JA (1994) Obstructions to shadowing when a Lyapunov exponent fluctuates about zero. Phys Rev Lett 73:1927\u20131930. https:\/\/doi.org\/10.1103\/PhysRevLett.73.1927","journal-title":"Phys Rev Lett"},{"issue":"2","key":"9824_CR42","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/BF01209065","volume":"1","author":"HDI Abarbanel","year":"1991","unstructured":"Abarbanel HDI, Brown R, Kennel MB (1991) Variation of Lyapunov exponents on a strange attractor. J Nonlinear Sci 1(2):175\u2013199. https:\/\/doi.org\/10.1007\/BF01209065","journal-title":"J Nonlinear Sci"},{"issue":"1","key":"9824_CR43","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/S0378-4371(00)00591-4","volume":"292","author":"H Shibata","year":"2001","unstructured":"Shibata H (2001) Ks entropy and mean Lyapunov exponent for coupled map lattices. Physica A 292(1):182\u2013192. https:\/\/doi.org\/10.1016\/S0378-4371(00)00591-4","journal-title":"Physica A"},{"key":"9824_CR44","doi-asserted-by":"crossref","unstructured":"Sait\u00f4 N, Ichimura A (1979) Ergodic components in the stochastic region in a Hamiltonian system. In: Casati G, Ford J (eds) Stochastic Behavior in Classical and Quantum Hamiltonian Systems. Springer, Berlin, Heidelberg, pp 137\u2013144","DOI":"10.1007\/BFb0021740"},{"issue":"2","key":"9824_CR45","first-page":"183","volume":"14","author":"G Ochs","year":"1999","unstructured":"Ochs G (1999) Stability of Oseledets spaces is equivalent to stability of Lyapunov exponents. Dyn Stab Syst 14(2):183\u2013201","journal-title":"Dyn Stab Syst"},{"issue":"5","key":"9824_CR46","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1143\/PTP.83.875","volume":"83","author":"K Geist","year":"1990","unstructured":"Geist K, Parlitz U, Lauterborn W (1990) Comparison of Different Methods for Computing Lyapunov Exponents. Progress Theoret Phys 83(5):875\u2013893. https:\/\/doi.org\/10.1143\/PTP.83.875 (https:\/\/academic.oup.com\/ptp\/article-pdf\/83\/5\/875\/5302061\/83-5-875.pdf)","journal-title":"Progress Theoret Phys"},{"key":"9824_CR47","doi-asserted-by":"crossref","unstructured":"Arnold L (1995) Random dynamical systems. Dyn Syst 1\u201343","DOI":"10.1007\/BFb0095238"},{"issue":"1","key":"9824_CR48","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF02128236","volume":"15","author":"G Benettin","year":"1980","unstructured":"Benettin G, Galgani L, Giorgilli A, Strelcyn J.-M (1980) Lyapunov characteristic exponents for smooth dynamical systems and for Hamiltonian systems; a method for computing all of them. part 1: Theory. Meccanica 15(1):9\u201320","journal-title":"Meccanica"},{"issue":"3","key":"9824_CR49","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/0168-9274(95)00033-Q","volume":"17","author":"L Dieci","year":"1995","unstructured":"Dieci L, Van Vleck ES (1995) Computation of a few Lyapunov exponents for continuous and discrete dynamical systems. Appl Num Math 17(3):275\u2013291","journal-title":"Appl Num Math"},{"key":"9824_CR50","unstructured":"Goodfellow IJ, Bengio Y, Courville A (2016) Deep Learning. MIT Press, Cambridge, MA, USA . http:\/\/www.deeplearningbook.org"},{"key":"9824_CR51","unstructured":"Chollet F (2021) Deep Learning with Python. Simon and Schuster, ???"},{"key":"9824_CR52","doi-asserted-by":"crossref","unstructured":"Liii Pearson K (1901) on lines and planes of closest fit to systems of points in space. The London. Edinburgh Dublin Philos Mag J Sci 2(11):559\u2013572","DOI":"10.1080\/14786440109462720"},{"key":"9824_CR53","doi-asserted-by":"publisher","first-page":"70","DOI":"10.3389\/frai.2020.00070","volume":"3","author":"K Su","year":"2020","unstructured":"Su K, Shlizerman E (2020) Clustering and recognition of spatiotemporal features through interpretable embedding of sequence to sequence recurrent neural networks. Front Artif Intell 3:70","journal-title":"Front Artif Intell"},{"key":"9824_CR54","unstructured":"Maaten L, Hinton G(2008) Visualizing data using t-sne. J Mach Learn Res 9(11)"},{"issue":"29","key":"9824_CR55","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","volume":"3","author":"L McInnes","year":"2018","unstructured":"McInnes L, Healy J, Saul N, Gro\u00dfberger L (2018) Umap: uniform manifold approximation and projection. J Open Sour Softw 3(29):861","journal-title":"J Open Sour Softw"},{"issue":"4","key":"9824_CR56","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neuron.2009.07.018","volume":"63","author":"D Sussillo","year":"2009","unstructured":"Sussillo D, Abbott LF (2009) Generating coherent patterns of activity from chaotic neural networks. Neuron 63(4):544\u2013557","journal-title":"Neuron"},{"issue":"2","key":"9824_CR57","doi-asserted-by":"publisher","first-page":"0191527","DOI":"10.1371\/journal.pone.0191527","volume":"13","author":"B DePasquale","year":"2018","unstructured":"DePasquale B, Cueva CJ, Rajan K, Escola GS, Abbott L (2018) full-FORCE: a target-based method for training recurrent networks. PLoS ONE 13(2):0191527","journal-title":"PLoS ONE"},{"key":"9824_CR58","unstructured":"Karpathy A, Johnson J, Fei-Fei L (2015) Visualizing and understanding recurrent networks. arXiv e-prints, 1506"},{"issue":"11","key":"9824_CR59","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"9824_CR60","unstructured":"Bai S, Zico\u00a0Kolter J, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv e-prints, 1803"},{"key":"9824_CR61","unstructured":"Rusch TK, Mishra S, Erichson NB, Mahoney MW (2022) Long expressive memory for sequence modeling"},{"key":"9824_CR62","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"issue":"1","key":"9824_CR63","doi-asserted-by":"publisher","first-page":"4950","DOI":"10.1038\/s41467-018-07210-0","volume":"9","author":"B Lusch","year":"2018","unstructured":"Lusch B, Kutz JN, Brunton SL (2018) Deep learning for universal linear embeddings of nonlinear dynamics. Nat Commun 9(1):4950. https:\/\/doi.org\/10.1038\/s41467-018-07210-0","journal-title":"Nat Commun"},{"issue":"41","key":"9824_CR64","first-page":"1","volume":"22","author":"H Lange","year":"2021","unstructured":"Lange H, Brunton SL, Kutz JN (2021) From Fourier to Koopman: spectral methods for long-term time series prediction. J Mach Learn Res 22(41):1\u201338","journal-title":"J Mach Learn Res"},{"key":"9824_CR65","unstructured":"Morton J, Jameson A, Kochenderfer MJ, Witherden F (2018) Deep dynamical modeling and control of unsteady fluid flows. Adv Neural Inform Process Syst 31"},{"key":"9824_CR66","doi-asserted-by":"publisher","unstructured":"Erichson NB, Muehlebach M, Mahoney MW (2019) Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction. arXiv . https:\/\/doi.org\/10.48550\/ARXIV.1905.10866","DOI":"10.48550\/ARXIV.1905.10866"},{"key":"9824_CR67","unstructured":"Azencot O, Erichson NB, Lin V, Mahoney M(2020) Forecasting sequential data using consistent Koopman autoencoders. In: International Conference on Machine Learning, pp 475\u2013 485 . PMLR"}],"updated-by":[{"DOI":"10.1007\/s00521-024-10366-0","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000}}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09824-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-09824-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09824-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T04:06:31Z","timestamp":1732334791000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-09824-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,2]]},"references-count":67,"journal-issue":{"issue":"34","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["9824"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-09824-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,2]]},"assertion":[{"value":"20 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2024","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s00521-024-10366-0","URL":"https:\/\/doi.org\/10.1007\/s00521-024-10366-0","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The datasets analyzed during the current study, as well as the code used to generate results, are available in the LyapunovAutoEncode repository,\n                      \n                      .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data availability"}}]}}