{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T14:01:36Z","timestamp":1782828096966,"version":"3.54.5"},"reference-count":46,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T00:00:00Z","timestamp":1777075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Most neural architectures model time as a one-dimensional real-valued variable, constraining temporal reasoning to sequential propagation along a single axis. We introduce Complex-Time Neural Networks (CTNN), a new class of architectures in which temporal coordinates are elements of the complex plane T=t+i\u03c4\u2208C, where ReT preserves chronological ordering and ImT encodes an orthogonal experiential dimension. Within this geometry, ImT&lt;0 defines a memory domain enabling retrospective retrieval, ImT=0 corresponds to present-moment computation, and ImT&gt;0 defines an imagination domain for prospective projection. We prove the Expressive Separation Theorem (Theorem 1), establishing that, within the temporally coupled function class GTCP and under explicit Assumptions A1\u2013A4 (in particular the bounded projection Assumption A3), CTNN accesses temporally coupled functions at O(1) cost with respect to temporal distance \u03941, \u03942, while real-time architectures incur \u03a9(\u03941 + \u03942) sequential steps. For layered compositions, this yields an exponential composition gap within GTCP under A1\u2013A4. These advantages hold under the stated assumptions and may not directly generalize to broader function classes or large-scale settings where A3 cannot be maintained. Therefore, Theorem 1 provides a formal separation result for GTCP, while CTNN more broadly defines a geometric framework for temporal computation. As the first concrete instantiation of this framework, we develop Complex-Time Convolutional Neural Networks (CTCNN). CTCNN achieves state-of-the-art performance on Something-Something V2 (70.2\u00b10.4%,\u00a0+1.1% over VideoMAE v2, p&lt;0.01), strong performance on Kinetics-400 (78.4\u00b10.3%), and substantial gains on Long Range Arena Path-X (87.3%\u00a0vs.\u00a079.6%,\u00a0+7.7%), using 3.4\u00d7 fewer parameters than VideoMAE v2. Learnable angular parameters \u03b1 and \u03b2 provide computationally interpretable parameters related to memory-access span and prospection breadth, with values varying systematically across task families.<\/jats:p>","DOI":"10.3390\/a19050334","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:55:39Z","timestamp":1777370139000},"page":"334","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Complex-Time Neural Networks: Geometric Temporal Access for Long-Range Reasoning"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3119-4608","authenticated-orcid":false,"given":"Gerardo","family":"Iovane","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Salerno, 84084 Fisciano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Iovane","sequence":"additional","affiliation":[{"name":"Liceo Scientifico Statale Francesco Severi, 84100 Salerno, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"De Rosa","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Salerno, 84084 Fisciano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Iovane, G., and Iovane, G. (2025). Sophimatics: A Two-Dimensional Temporal Cognitive Architecture for Paradox-Resilient Artificial Intelligence. Big Data Cogn. Comput., 9.","DOI":"10.3390\/bdcc9120314"},{"key":"ref_4","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":"ref_5","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014, January 25\u201329). Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_8","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015, January 13\u201316). Learning spatiotemporal features with 3D convolutional networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref_10","unstructured":"Simonyan, K., and Zisserman, A. (2014, January 9\u201311). Two-stream convolutional networks for action recognition in videos. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_11","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_12","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Minneapolis, MN, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hirose, A. (2003). Complex-Valued Neural Networks: Theories and Applications, World Scientific.","DOI":"10.1142\/5345"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1406","DOI":"10.1109\/JAS.2022.105743","article-title":"Complex-valued neural networks: A comprehensive survey","volume":"9","author":"Lee","year":"2022","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_15","unstructured":"Trabelsi, C., Bilaniuk, O., Zhang, Y., Serdyuk, D., Subramanian, S., Santos, J.F., Mehri, S., Rostamzadeh, N., Bengio, Y., and Pal, C. (May, January 30). Deep complex networks. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Virtanen, T., Plumbley, M.D., and Ellis, D. (2018). Computational Analysis of Sound Scenes and Events, Springer.","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1038\/nphoton.2017.93","article-title":"Deep learning with coherent nanophotonic circuits","volume":"11","author":"Shen","year":"2017","journal-title":"Nat. Photonics"},{"key":"ref_18","unstructured":"Graves, A., Wayne, G., and Danihelka, I. (2014). Neural Turing machines. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1038\/nature20101","article-title":"Hybrid computing using a neural network with dynamic external memory","volume":"538","author":"Graves","year":"2016","journal-title":"Nature"},{"key":"ref_20","unstructured":"Sukhbaatar, S., Szlam, A., Weston, J., and Fergus, R. (2015, January 7\u201312). End-to-end memory networks. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada."},{"key":"ref_21","unstructured":"Tay, Y., Dehghani, M., Abnar, S., Shen, Y., Bahri, D., Pham, P., Rao, J., Yang, L., Ruder, S., and Metzler, D. (2021, January 3\u20137). Long Range Arena: A benchmark for efficient transformers. Proceedings of the International Conference on Learning Representations (ICLR), Online Virtual Conference."},{"key":"ref_22","unstructured":"Gu, A., Goel, K., and R\u00e9, C. (2022, January 25\u201329). Efficiently modeling long sequences with structured state spaces. Proceedings of the International Conference on Learning Representations (ICLR), Online Virtual Conference."},{"key":"ref_23","unstructured":"Gu, A., and Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2530","DOI":"10.1109\/TSMC.2023.3345365","article-title":"On State-Constrained Containment Control for Nonlinear Multiagent Systems Using Event-Triggered Input","volume":"54","author":"Wang","year":"2024","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5012","DOI":"10.1109\/TASE.2023.3306101","article-title":"Optimized Adaptive Finite-Time Consensus Control for Stochastic Nonlinear Multiagent Systems with Non-Affine Nonlinear Faults","volume":"21","author":"Wang","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Demertzis, K., Papadopoulos, G.D., Iliadis, L., and Magafas, L. (2022). A Comprehensive Survey on Nanophotonic Neural Networks: Architectures, Training Methods, Optimization, and Activations Functions. Sensors, 22.","DOI":"10.3390\/s22030720"},{"key":"ref_27","unstructured":"Zee, A. (2010). Quantum Field Theory in a Nutshell, Princeton University Press. [2nd ed.]."},{"key":"ref_28","unstructured":"Peskin, M.E., and Schroeder, D.V. (1995). An Introduction to Quantum Field Theory, Addison-Wesley."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1038\/nrn2213","article-title":"Remembering the past to imagine the future: The prospective brain","volume":"8","author":"Schacter","year":"2007","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1016\/j.neuron.2011.07.012","article-title":"Hippocampal \u2018time cells\u2019 bridge the gap in memory for discontiguous events","volume":"71","author":"MacDonald","year":"2011","journal-title":"Neuron"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.tics.2015.04.006","article-title":"Hierarchical process memory: Memory as an integral component of information processing","volume":"19","author":"Hasson","year":"2015","journal-title":"Trends Cogn. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1017\/S0140525X01003922","article-title":"The magical number 4 in short-term memory: A reconsideration of mental storage capacity","volume":"24","author":"Cowan","year":"2001","journal-title":"Behav. Brain Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1073\/pnas.0610082104","article-title":"Neural substrates of envisioning the future","volume":"104","author":"Szpunar","year":"2007","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_34","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_35","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_36","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_37","unstructured":"Chen, W., Wang, X., and Wang, W.Y. (2021). A Dataset for Answering Time-Sensitive Questions. arXiv."},{"key":"ref_38","unstructured":"Soomro, K., Zamir, A.R., and Shah, M. (2012). UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1488","DOI":"10.1109\/TMI.2018.2820120","article-title":"Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss","volume":"37","author":"Quan","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_40","unstructured":"Cover, T.M., and Thomas, J.A. (2006). Elements of Information Theory, Wiley-Interscience. [2nd ed.]."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Tavallaee, M., Bagheri, E., Lu, W., and Ghorbani, A.A. (2009, January 8\u201310). A detailed analysis of the KDD CUP 99 data set. Proceedings of the IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA), Ottawa, ON, Canada.","DOI":"10.1109\/CISDA.2009.5356528"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Sharafaldin, I., Lashkari, A.H., and Ghorbani, A.A. (2018, January 22\u201324). Toward generating a new intrusion detection dataset and intrusion traffic characterization. Proceedings of the International Conference on Information Systems Security and Privacy (ICISSP), Funchal, Portugal.","DOI":"10.5220\/0006639801080116"},{"key":"ref_43","unstructured":"Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., McGrew, B., Tobin, J., Abbeel, P., and Zaremba, W. (2017, January 4\u20139). Hindsight experience replay. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_44","unstructured":"Fan, A., Lewis, M., and Dauphin, Y. (2018, January 15\u201320). Hierarchical neural story generation. Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Melbourne, Australia."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","article-title":"The Arcade Learning Environment: An evaluation platform for general agents","volume":"47","author":"Bellemare","year":"2013","journal-title":"J. Artif. Intell. Res."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1007\/s11263-018-01144-2","article-title":"Video enhancement with task-oriented flow","volume":"127","author":"Xue","year":"2019","journal-title":"Int. J. Comput. Vis."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/334\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T07:47:11Z","timestamp":1778658431000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/334"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,25]]},"references-count":46,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["a19050334"],"URL":"https:\/\/doi.org\/10.3390\/a19050334","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,25]]}}}