Добірка наукової літератури з теми "Neural ODEs"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Neural ODEs".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Neural ODEs"
Filici, Cristian. "On a Neural Approximator to ODEs." IEEE Transactions on Neural Networks 19, no. 3 (March 2008): 539–43. http://dx.doi.org/10.1109/tnn.2007.915109.
Повний текст джерелаZhou, Fan, and Liang Li. "Forecasting Reservoir Inflow via Recurrent Neural ODEs." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 17 (May 18, 2021): 15025–32. http://dx.doi.org/10.1609/aaai.v35i17.17763.
Повний текст джерелаCui, Wenjun, Honglei Zhang, Haoyu Chu, Pipi Hu, and Yidong Li. "On robustness of neural ODEs image classifiers." Information Sciences 632 (June 2023): 576–93. http://dx.doi.org/10.1016/j.ins.2023.03.049.
Повний текст джерелаFronk, Colby, and Linda Petzold. "Interpretable polynomial neural ordinary differential equations." Chaos: An Interdisciplinary Journal of Nonlinear Science 33, no. 4 (April 2023): 043101. http://dx.doi.org/10.1063/5.0130803.
Повний текст джерелаZhou, Fan, Liang Li, Kunpeng Zhang, and Goce Trajcevski. "Urban flow prediction with spatial–temporal neural ODEs." Transportation Research Part C: Emerging Technologies 124 (March 2021): 102912. http://dx.doi.org/10.1016/j.trc.2020.102912.
Повний текст джерелаEsteve-Yagüe, Carlos, and Borjan Geshkovski. "Sparsity in long-time control of neural ODEs." Systems & Control Letters 172 (February 2023): 105452. http://dx.doi.org/10.1016/j.sysconle.2022.105452.
Повний текст джерелаKuptsov, P. V., A. V. Kuptsova, and N. V. Stankevich. "Artificial Neural Network as a Universal Model of Nonlinear Dynamical Systems." Nelineinaya Dinamika 17, no. 1 (2021): 5–21. http://dx.doi.org/10.20537/nd210102.
Повний текст джерелаGrunbacher, Sophie, Ramin Hasani, Mathias Lechner, Jacek Cyranka, Scott A. Smolka, and Radu Grosu. "On the Verification of Neural ODEs with Stochastic Guarantees." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 13 (May 18, 2021): 11525–35. http://dx.doi.org/10.1609/aaai.v35i13.17372.
Повний текст джерелаRuiz-Balet, Domènec, Elisa Affili, and Enrique Zuazua. "Interpolation and approximation via Momentum ResNets and Neural ODEs." Systems & Control Letters 162 (April 2022): 105182. http://dx.doi.org/10.1016/j.sysconle.2022.105182.
Повний текст джерелаCuchiero, Christa, Martin Larsson, and Josef Teichmann. "Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs." SIAM Journal on Mathematics of Data Science 2, no. 3 (January 2020): 901–19. http://dx.doi.org/10.1137/19m1284117.
Повний текст джерелаДисертації з теми "Neural ODEs"
Monsel, Thibault. "Deep Learning for Partially Observed Dynamical Systems." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASG113.
Повний текст джерелаPartial Differential Equations (PDEs) are the cornerstone of modeling dynamical systems across various scientific disciplines. Traditionally, scientists employ a rigorous methodology to interact with physical processes, collect empirical data, and derive theoretical models. However, even when these models align closely with observed data, which is often not the case, the necessary simplifications made for study and simulation can obscure our understanding of the underlying phenomena.This thesis explores how data acquired from dynamical systems can be utilized to improve and/or derive better models. The manuscript focuses particularly on partially observed dynamics, where the system's full state is not completely measured or observed. Through the theory of partially observed systems, including the Mori-Zwanzig formalism and Takens' theorem, we motivate a non-Markovian structure, specifically Delay Differential Equations (DDEs).By combining the expressive power of neural networks with DDEs, we propose novel models for partially observed systems. As neural network-based DDEs (Neural DDEs) are still in their infancy, we extend the current state of the art in this field by studying and benchmarking Neural DDE models with a-priori known arbitrary delay types across a variety of dynamical systems. These benchmarks include systems, with time-dependent and state-dependent delays. Building upon these investigations, we then explore the parameterization of constant delays in Neural DDEs. Our findings demonstrate that introducing learnable constant delays, as opposed to fixed delay configurations, results in improved overall performance in dynamical system modeling and fitting.We then apply the non-Markovian Neural DDEs with learnable constant delays to dynamical system closure and correction modeling, demonstrating improved long-term accuracy compared to Ordinary Differential Equation terms. Lastly, we explore the use of Neural DDEs in the context of Model Predictive Control (MPC) for controlling dynamical systems
Tacuri, Patrícia Hilario. "Equações diferenciais funcionais neutras, comportamento assintótico e representação." Universidade de São Paulo, 2013. http://www.teses.usp.br/teses/disponiveis/55/55135/tde-02042013-104407/.
Повний текст джерелаThe aim of this work is to investigate qualitative properties of neutral functional differential equations (NFDEs) and introduce a general class of equations called measure NFDE . We obtain results on the asymptotic behavior for a class of NFDEs with periodic coefficients, where the period and delay are rationally related. Moreover, we show that the exponential dichotomy of the solution operator of non autonomous retarded functional differential equations (RFDEs) implies the existence of bounded solutions to the associated non homogeneous RFDEs. Finally, using the theory of generalized ordinary differential equations (generalized ODEs), we obtain results of existence and uniqueness, continuous dependence on parameters of the solutions of measure NFDEs. The new results presented in this work are contained in the articles [31,43]
Khudhair, Ali Dheyaa. "VECTOR QUANTIZATION USING ODE BASED NEURAL NETWORK WITH VARYING VIGILANCE PARAMETER." OpenSIUC, 2012. https://opensiuc.lib.siu.edu/dissertations/478.
Повний текст джерелаKortmann, Konstantin. "Abriss und Neubau oder Kernsanierung? eine empirische Untersuchung zur Nutzungsdauer von Wohngebäuden des 20. Jahrhunderts im Ruhrgebiet." Köln R. Müller, 2007. http://d-nb.info/990659798/04.
Повний текст джерелаWermann, Silke. "Analytik von phenolischen Substanzen und Epoxiden in Materialien mit Lebensmittel- und/oder dermalem Kontakt." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2008. http://nbn-resolving.de/urn:nbn:de:bsz:14-ds-1228839995955-73499.
Повний текст джерелаHorečný, Peter. "Metody segmentace obrazu s malými trénovacími množinami." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-412996.
Повний текст джерелаGarnier, Aurélie. "Dynamiques neuro-gliales locales et réseaux complexes pour l'étude de la relation entre structure et fonction cérébrales." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066562/document.
Повний текст джерелаA current issue in neuroscience is to elaborate computational models that are able to reproduce experimental data recorded with various imaging methods, and allowing us to study the relationship between structure and function in the human brain. The modeling objectives of this work are two scales and the model analysis need the development of specific theoretical and numerical tools. At the local scale, we propose a new ordinary differential equations model generating neuronal activities. We characterize and classify the behaviors the model can generate, we compare the model outputs to experimental data and we identify the dynamical structures of the neural compartment underlying the generation of pathological patterns. We then extend this approach to a new neuro-glial mass model: a bilateral coupling between the neural compartment and a new one modeling the impact of astrocytes on neurotransmitter concentrations and the feedback of these concentrations on neural activity is developed. We obtain a theoretical characterization of these feedbacks impact on neuronal excitability by formalizing the variation of a bifurcation value as a problem of optimization under constraint. Finally, we propose a network model, which node dynamics are based on the local neuro-glial mass model, embedding a neuronal coupling and a glial one. We numerically observe the differential propagations of information according to each of these coupling types and their cumulated impact, we highlight qualitatively distinct patterns of neural and glial activities of each node, and link the transitions between behaviors with the dynamical structures identified in the local models
Garnier, Aurélie. "Dynamiques neuro-gliales locales et réseaux complexes pour l'étude de la relation entre structure et fonction cérébrales." Electronic Thesis or Diss., Paris 6, 2015. http://www.theses.fr/2015PA066562.
Повний текст джерелаA current issue in neuroscience is to elaborate computational models that are able to reproduce experimental data recorded with various imaging methods, and allowing us to study the relationship between structure and function in the human brain. The modeling objectives of this work are two scales and the model analysis need the development of specific theoretical and numerical tools. At the local scale, we propose a new ordinary differential equations model generating neuronal activities. We characterize and classify the behaviors the model can generate, we compare the model outputs to experimental data and we identify the dynamical structures of the neural compartment underlying the generation of pathological patterns. We then extend this approach to a new neuro-glial mass model: a bilateral coupling between the neural compartment and a new one modeling the impact of astrocytes on neurotransmitter concentrations and the feedback of these concentrations on neural activity is developed. We obtain a theoretical characterization of these feedbacks impact on neuronal excitability by formalizing the variation of a bifurcation value as a problem of optimization under constraint. Finally, we propose a network model, which node dynamics are based on the local neuro-glial mass model, embedding a neuronal coupling and a glial one. We numerically observe the differential propagations of information according to each of these coupling types and their cumulated impact, we highlight qualitatively distinct patterns of neural and glial activities of each node, and link the transitions between behaviors with the dynamical structures identified in the local models
Bělohlávek, Jiří. "Agent pro kurzové sázení." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2008. http://www.nusl.cz/ntk/nusl-235980.
Повний текст джерелаGeraldes, Carlos José Brás. "Aplicação das redes neuronais aditivas generalizadas à Medicina." Doctoral thesis, 2017. http://hdl.handle.net/10362/20114.
Повний текст джерелаABSTRACT: The application of artificial neural networks has been increasing in many areas of knowledge, much due to the flexibility that features these models and they allow to model data not only from more complex situations, such as pattern recognition and voice data but also simpler such as, for example, those that reflect relationships between multiple independent variables, and a outcome (dependent variable). A widely used architecture is the Multi Layer Perceptron (MLP). However, despite its popularity in several areas of knowledge, this model is less used in the clinical context that the Generalized Linear Models (GLMs) and the Generalized Additive Models (GAMs), due to the fact that, the MLP works as a black box. In the other hand, the Generalized Additive Neural Network (GANN) besides producing good estimates, allows the interpretation of the effect of each covariate on the outcome. Those features makes this type of neural network much more promising in the clinical area. On the other hand, concerning the regression models, several authors have reported that a bad choice of the link function can affect, in some cases, the model performance; so, studies have been developed in order to solve this issue by the introduction of a flexible link function either (parametric or nonparametric). In the case of a GANN, given the low number of studies about this architecture, we find that nothing has been done regarding the estimation of the link function using parametric methods, becoming this one goal of the present study. The link function estimation by using nonparametric methods was also approached. Another goal included the implement of methods for the determination of confidence intervals of the partial functions and the odds ratio function, which substantially improved the interpretability of the results of this type of neural network.
Книги з теми "Neural ODEs"
Seiferlein, Werner. Vor- und Nachteile von Neubau oder Sanierung im Bestand. Wiesbaden: Springer Fachmedien Wiesbaden, 2019. http://dx.doi.org/10.1007/978-3-658-25125-3.
Повний текст джерела1882-1945, Neurath Otto, Neurath Paul, and Nemeth Elisabeth, eds. Otto Neurath, oder, Die Einheit von Wissenschaft und Gesellschaft. Wien: Böhlau, 1994.
Знайти повний текст джерелаMazzola, Guerino, Gérard Milmeister, and Jody Weissmann. Comprehensive Mathematics for Computer Scientists 2: Calculus and ODEs, Splines, Probability, Fourier and Wavelet Theory, Fractals and Neural Networks, Categories and Lambda Calculus. Springer London, Limited, 2006.
Знайти повний текст джерелаNeuman, Susan B. Changing the Odds for Children at Risk. Greenwood Publishing Group, Inc., 2008. http://dx.doi.org/10.5040/9798400624575.
Повний текст джерелаFun Palace 200X: Der Berliner Schlossplatz : Abriss, Neubau oder grüne Wiese? Berlin: Martin Schmitz, 2005.
Знайти повний текст джерелаDesign, Kawea. Hausbautagebuch: Das Bautagebuch Für Alle Bauherren, Bauleiter, Familien Egal Ob Neubau Oder Renovierung. Independently Published, 2021.
Знайти повний текст джерелаAufbau, Umbau oder Neubau einer Bibliothek: Informationsquellen zu den Themen Raum und Einrichtung. Saarbrücken: VDM Verlag Dr. Müller, 2008.
Знайти повний текст джерелаSeiferlein, Werner. Vor- und Nachteile von Neubau oder Sanierung im Bestand: Schnelleinstieg für Architekten und Bauingenieure. Springer Vieweg, 2019.
Знайти повний текст джерелаHistorische Eisenbahnbrücken. Fraunhofer IRB Verlag, 2019. http://dx.doi.org/10.51202/9783738802528.
Повний текст джерелаPublikationen, M. Krohne. Bauplaner Für Mein Traumhaus: Ein Nice Durchorganisierter Kalender Für Dein Zuhause - Ob Neubau Oder Renovierung - Behalte Den Überblick Wie ein Pro. Independently Published, 2019.
Знайти повний текст джерелаЧастини книг з теми "Neural ODEs"
Grouchy, Paul, and Gabriele M. T. D’Eleuterio. "Supplanting Neural Networks with ODEs in Evolutionary Robotics." In Lecture Notes in Computer Science, 299–308. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-17298-4_31.
Повний текст джерелаJosias, Shane, and Willie Brink. "Jacobian Norm Regularisation and Conditioning in Neural ODEs." In Artificial Intelligence Research, 31–45. Cham: Springer Nature Switzerland, 2022. http://dx.doi.org/10.1007/978-3-031-22321-1_3.
Повний текст джерелаChen, Eric Z., Terrence Chen, and Shanhui Sun. "MRI Image Reconstruction via Learning Optimization Using Neural ODEs." In Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, 83–93. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-59713-9_9.
Повний текст джерелаPandey, Prashant, Aleti Vardhan, Mustafa Chasmai, Tanuj Sur, and Brejesh Lall. "Adversarially Robust Prototypical Few-Shot Segmentation with Neural-ODEs." In Lecture Notes in Computer Science, 77–87. Cham: Springer Nature Switzerland, 2022. http://dx.doi.org/10.1007/978-3-031-16452-1_8.
Повний текст джерелаXu, Junshen, Eric Z. Chen, Xiao Chen, Terrence Chen, and Shanhui Sun. "Multi-scale Neural ODEs for 3D Medical Image Registration." In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, 213–23. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-87202-1_21.
Повний текст джерелаKloberdanz, Eliska, and Wei Le. "S-SOLVER: Numerically Stable Adaptive Step Size Solver for Neural ODEs." In Artificial Neural Networks and Machine Learning – ICANN 2023, 388–400. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44201-8_32.
Повний текст джерелаBhaya, Amit, Fernando A. Pazos, and Eugenius Kaszkurewicz. "Comparative Study of the CG and HBF ODEs Used in the Global Minimization of Nonconvex Functions." In Artificial Neural Networks – ICANN 2009, 668–77. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009. http://dx.doi.org/10.1007/978-3-642-04274-4_69.
Повний текст джерелаJulmi, Christian, Anna Eifert, Jakob E. Dammert, and Sebastian Wittwer. "Typen von Atmosphären." In essentials, 43–49. Wiesbaden: Springer Fachmedien Wiesbaden, 2024. http://dx.doi.org/10.1007/978-3-658-45074-8_5.
Повний текст джерелаFlorack, Martin. "Renovierung oder Neubau?" In Regierungszentralen, 143–67. Wiesbaden: VS Verlag für Sozialwissenschaften, 2011. http://dx.doi.org/10.1007/978-3-531-93016-9_6.
Повний текст джерелаBörgers, Christoph. "The Classical Hodgkin-Huxley ODEs." In An Introduction to Modeling Neuronal Dynamics, 15–21. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-51171-9_3.
Повний текст джерелаТези доповідей конференцій з теми "Neural ODEs"
Sochopoulos, Andreas, Michael Gienger, and Sethu Vijayakumar. "Learning Deep Dynamical Systems using Stable Neural ODEs." In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 11163–70. IEEE, 2024. https://doi.org/10.1109/iros58592.2024.10801826.
Повний текст джерелаChen, Zhang, Wei Zhu, Jingsui Li, Hanlin Bian, and Chao Pei. "Model Reconstruction Based on Physical-Informed Polynomial Neural ODEs." In 2024 IEEE 13th Data Driven Control and Learning Systems Conference (DDCLS), 91–97. IEEE, 2024. http://dx.doi.org/10.1109/ddcls61622.2024.10606885.
Повний текст джерелаZimmering, Bernd, Jan-Philipp Roche, and Oliver Niggemann. "Enhancing Nonlinear Electrical Circuit Modeling with Prior Knowledge-Infused Neural ODEs." In 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), 01–08. IEEE, 2024. http://dx.doi.org/10.1109/etfa61755.2024.10711112.
Повний текст джерелаNawaz, Farhad, Tianyu Li, Nikolai Matni, and Nadia Figueroa. "Learning Complex Motion Plans using Neural ODEs with Safety and Stability Guarantees." In 2024 IEEE International Conference on Robotics and Automation (ICRA), 17216–22. IEEE, 2024. http://dx.doi.org/10.1109/icra57147.2024.10611584.
Повний текст джерелаBoersma, Sjoerd, and Xiaodong Cheng. "A Bayesian Neural ODE for a Lettuce Greenhouse." In 2024 IEEE Conference on Control Technology and Applications (CCTA), 782–86. IEEE, 2024. http://dx.doi.org/10.1109/ccta60707.2024.10666596.
Повний текст джерелаXu, Yucheng, Nanbo Li, Arushi Goel, Zonghai Yao, Zijian Guo, Hamidreza Kasaei, Mohammadreza Kasaei, and Zhibin Li. "TiV-ODE: A Neural ODE-based Approach for Controllable Video Generation From Text-Image Pairs." In 2024 IEEE International Conference on Robotics and Automation (ICRA), 14645–52. IEEE, 2024. http://dx.doi.org/10.1109/icra57147.2024.10610149.
Повний текст джерелаAntal, Ákos, Bálint Szabó, Ákos Szlávecz, Katalin Kovács, J. Geoffrey Chase, and Balázs Benyó. "Applying Neural ODE-Based Cardiovascular Model Identification for Experimental Data Analysis." In 2024 IEEE 18th International Symposium on Applied Computational Intelligence and Informatics (SACI), 000437–42. IEEE, 2024. http://dx.doi.org/10.1109/saci60582.2024.10619737.
Повний текст джерелаZiegelman, Liran, and Manuel E. Hernandez. "Application of a Neural ODE to Classify Motion Control Strategy using EEG." In 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 1–4. IEEE, 2024. https://doi.org/10.1109/embc53108.2024.10782326.
Повний текст джерелаJiang, Yu-Chen, and Jun-Min Wang. "Neural operators of backstepping controller gain kernels for an ODE cascaded with a reaction-diffusion equation." In 2024 43rd Chinese Control Conference (CCC), 1099–104. IEEE, 2024. http://dx.doi.org/10.23919/ccc63176.2024.10661479.
Повний текст джерелаZhao, Shiyao, Yucheng Xu, Mohammadreza Kasaei, Mohsen Khadem, and Zhibin Li. "Neural ODE-based Imitation Learning (NODE-IL): Data-Efficient Imitation Learning for Long-Horizon Multi-Skill Robot Manipulation." In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 8524–30. IEEE, 2024. https://doi.org/10.1109/iros58592.2024.10802736.
Повний текст джерелаЗвіти організацій з теми "Neural ODEs"
Jain, Anand. Neural ODEs for Light Curves Classifying and Approximating Light Curves. Office of Scientific and Technical Information (OSTI), August 2019. http://dx.doi.org/10.2172/1614721.
Повний текст джерелаFiliz, Ibrahim. Overconfidence: Der Einfluss positiver und negativer Affekte. Sonderforschungsgruppe Institutionenanalyse, 2017. http://dx.doi.org/10.46850/sofia.9783941627598.
Повний текст джерелаZiegler, Britta. Die archäologischen Untersuchungen des Wasserschlosses Allersberg 2008. Otto-Friedrich-Universität Bamberg, 2023. http://dx.doi.org/10.20378/irb-91142.
Повний текст джерела