Search

Your search keyword '"Csiszar, A."' showing total 3,641 results
Start Over Author "Csiszar, A."
3,641 results on '"Csiszar, A."'

1. Parameter estimation of epidemic spread in two-layer random graphs by classical and machine learning methods

Author

Backhausz, Ágnes, Bognár, Edit, Csiszár, Villő, Tárkányi, Damján, and Zempléni, András

Subjects
Computer Science - Social and Information Networks, Quantitative Biology - Populations and Evolution, 62M45
Abstract

Our main goal in this paper is to quantitatively compare the performance of classical methods to XGBoost and convolutional neural networks in a parameter estimation problem for epidemic spread. As we use flexible two-layer random graphs as the underlying network, we can also study how much the structure of the graphs in the training set and the test set can differ while to get a reasonably good estimate. In addition, we also examine whether additional information (such as the average degree of infected vertices) can help improving the results, compared to the case when we only know the time series consisting of the number of susceptible and infected individuals. Our simulation results also show which methods are most accurate in the different phases of the epidemic., Comment: 16 pages, 7 figures

Published
2024

7. Linking peripheral atherosclerosis to blood–brain barrier disruption: elucidating its role as a manifestation of cerebral small vessel disease in vascular cognitive impairment

Author

Nyúl-Tóth, Ádám, Patai, Roland, Csiszar, Anna, Ungvari, Anna, Gulej, Rafal, Mukli, Peter, Yabluchanskiy, Andriy, Benyo, Zoltan, Sotonyi, Peter, Prodan, Calin I., Liotta, Eric M., Toth, Peter, Elahi, Fanny, Barsi, Péter, Maurovich-Horvat, Pál, Sorond, Farzaneh A., Tarantini, Stefano, and Ungvari, Zoltan

Published
2024
Full Text
View/download PDF

8. PLOTO: Improved IWW Resilience Using Predictive Modelling, Environmentally Sustainable and Emerging Digital Technologies and Tools

Author

Liparas, Dimitris, Vamvatsikos, Dimitrios, Drivas, Ioannis, Zanetti, Anna, Pagkozidis, Alexios, Bousmar, Didier, Budescu, Natalia, Szabó-Aranyi, Erzsébet, Melitsiotis, Alexis, Vokali, Themis, Melissianos, Vasileios, Barmpas, Fotios, Csiszár, Csaba, Letnik, Tomislav, Mezo, Gergely, Hardy, Joris, Soare, Romeo, Raileanu, Alina Beatrice, Kerényi, Judit, Hellsten, Antti, Akhgar, Babak, Series Editor, Gkotsis, Ilias, editor, Kavallieros, Dimitrios, editor, Stoianov, Nikolai, editor, Vrochidis, Stefanos, editor, and Diagourtas, Dimitrios, editor

Published
2025
Full Text
View/download PDF

10. Advancing prediction of age-related vascular cognitive impairment based on peripheral and retinal vascular health in a pilot study: a novel comprehensive assessment developed for a prospective workplace-based cohort (The Semmelweis Study)

Author

Csipo, Tamas, Lipecz, Agnes, Mukli, Peter, Péterfi, Anna, Szarvas, Zsofia, Ungvari, Anna, Alaoui, Lamyae El, Sándor, Márton, Kállai, Attila, Fekete, Mónika, Fülöp, Gábor Á., Tarantini, Stefano, Csiszar, Anna, Benyó, Zoltán, Sótonyi, Péter, Tabak, Adam G., Merkely, Béla, Yabluchanskiy, Andriy, and Ungvari, Zoltan

Published
2024
Full Text
View/download PDF

11. Longitudinal detection of gait alterations associated with hypertension-induced cerebral microhemorrhages in mice: predictive role of stride length and stride time asymmetry and increased gait entropy

Author

Ungvari, Zoltan, Muranyi, Mihaly, Gulej, Rafal, Negri, Sharon, Nyul-Toth, Adam, Csik, Boglarka, Patai, Roland, Conley, Shannon, Milan, Madison, Bagwell, Jonathan, O’Connor, Daniel, Tarantini, Amber, Yabluchanskiy, Andriy, Toth, Peter, Csiszar, Anna, Ungvari, Anna, Mukli, Peter, and Tarantini, Stefano

Published
2024
Full Text
View/download PDF

17. Estimating the parameters of epidemic spread on two-layer random graphs: a classical and a neural network approach

Author

Backhausz, Ágnes, Bognár, Edit, Csiszár, Villő, Tárkányi, Damján, and Zempléni, András

Subjects
Quantitative Biology - Populations and Evolution, Physics - Physics and Society, 62M45
Abstract

In this paper, we study the spread of a classical SIR process on a two-layer random network, where the first layer represents the households, while the second layer models the contacts outside the households by a random scale-free graph. We build a three-parameter graph, called polynomial model, where the new vertices are connected to the existing ones either uniformly, or preferentially, or by forming random triangles. We examine the effect of the graph's properties on the goodness of the estimation of the infection rate $\tau$, which is the most important parameter, determining the reproduction rate of the epidemic. In the classical maximum likelihood approach, to estimate $\tau$ one needs to approximate the number of SI edges between households, since the graph itself is supposed to be unobservable. Our simulation study reveals that the estimation is poorer at the beginning of the epidemic, for larger preferential attachment parameter of the graph, and for larger $\tau$. We present two heuristic improvement algorithms and establish our method to be robust to changes in average clustering of the graph model. We also extend a graph neural network (GNN) approach for estimating contagion dynamics for our two-layered graphs. We find that dense networks offer better training datasets. Moreover, GNN perfomance is measured better using the $l_2$ loss function rather than cross-entropy., Comment: 24 pages, 15 figures

Published
2023

18. We Can Always Reduce a Non-linear Dynamical System to Linear—At Least Locally—But Does It Help?

Author

Csiszár, Orsolya, Csiszár, Gábor, Kosheleva, Olga, Kreinovich, Vladik, Hoang Phuong, Nguyen, Kacprzyk, Janusz, Series Editor, Novikov, Dmitry A., Editorial Board Member, Shi, Peng, Editorial Board Member, Cao, Jinde, Editorial Board Member, Polycarpou, Marios, Editorial Board Member, Pedrycz, Witold, Editorial Board Member, Hoang Phuong, Nguyen, editor, Huyen Chau, Nguyen Thi, editor, and Kreinovich, Vladik, editor

Published
2024
Full Text
View/download PDF

19. Uninorm-like parametric activation functions for human-understandable neural models

Author

Csiszár, Orsolya, Pusztaházi, Luca Sára, Dénes-Fazakas, Lehel, Gashler, Michael S., Kreinovich, Vladik, and Csiszár, Gábor

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

We present a deep learning model for finding human-understandable connections between input features. Our approach uses a parameterized, differentiable activation function, based on the theoretical background of nilpotent fuzzy logic and multi-criteria decision-making (MCDM). The learnable parameter has a semantic meaning indicating the level of compensation between input features. The neural network determines the parameters using gradient descent to find human-understandable relationships between input features. We demonstrate the utility and effectiveness of the model by successfully applying it to classification problems from the UCI Machine Learning Repository.

Published
2022

20. Endothelial Colony-Forming Cells (ECFCs) in cerebrovascular aging: Focus on the pathogenesis of Vascular Cognitive Impairment and Dementia (VCID), and treatment prospects

Author

Negri, Sharon, Reyff, Zeke, Troyano-Rodriguez, Eva, Milan, Madison, Ihuoma, Jennifer, Tavakol, Sherwin, Shi, Helen, Patai, Roland, Jiang, Raymond, Mohon, Jonah, Boma-Iyaye, Jed, Ungvari, Zoltan, Csiszar, Anna, Yabluchanskiy, Andriy, Moccia, Francesco, and Tarantini, Stefano

Published
2025
Full Text
View/download PDF

21. The effects of time restricted feeding on age-related changes in the mouse retina

Author

Cade A. Huston, Madison Milan, Michaela L. Vance, Marisa A. Bickel, Lauren R. Miller, Sharon Negri, Clara Hibbs, Hannah Vaden, Lindsay Hayes, Anna Csiszar, Zoltan Ungvari, Andriy Yabluchanskiy, Stefano Tarantini, and Shannon M. Conley

Subjects
Time-restricted feeding, Aging, Retina, Vascular aging, Medicine, Biology (General), QH301-705.5
Abstract

Dietary modifications such as caloric restriction (CR) and intermittent fasting (IF) have gained popularity due to their proven health benefits in aged populations. In time restricted feeding (TRF), a form of intermittent fasting, the amount of time for food intake is regulated without restricting the caloric intake. TRF is beneficial for the central nervous system to support brain health in the context of aging. Therefore, we here ask whether TRF also exerts beneficial effects in the aged retina. We compared aged mice (24 months) on a TRF paradigm (access to food for six hours per day) for either 6 or 12 months against young control mice (8 months) and aged control mice on an ad libitum diet. We examined changes in the retina at the functional (electroretinography), structural (histology and fluorescein angiograms) and molecular (gene expression) level. TRF treatment showed amelioration of age-related reductions in both scotopic and photopic b-wave amplitudes suggesting benefits for retinal interneuron signaling. TRF did not affect age-related signs of retinal inflammation or microglial activation at either the molecular or histological level. Our data indicate that TRF helps preserve some aspects of retinal function that are decreased with aging, adding to our understanding of the health benefits that altered feeding patterns may confer.

Published
2024
Full Text
View/download PDF

26. The Semmelweis Study: a longitudinal occupational cohort study within the framework of the Semmelweis Caring University Model Program for supporting healthy aging

Author

Ungvari, Zoltan, Tabák, Adam G., Adany, Roza, Purebl, György, Kaposvári, Csilla, Fazekas-Pongor, Vince, Csípő, Tamás, Szarvas, Zsófia, Horváth, Krisztián, Mukli, Peter, Balog, Piroska, Bodizs, Robert, Ujma, Peter, Stauder, Adrienne, Belsky, Daniel W., Kovács, Illés, Yabluchanskiy, Andriy, Maier, Andrea B., Moizs, Mariann, Östlin, Piroska, Yon, Yongjie, Varga, Péter, Vokó, Zoltán, Papp, Magor, Takács, István, Vásárhelyi, Barna, Torzsa, Péter, Ferdinandy, Péter, Csiszar, Anna, Benyó, Zoltán, Szabó, Attila J., Dörnyei, Gabriella, Kivimäki, Mika, Kellermayer, Miklos, and Merkely, Bela

Published
2024
Full Text
View/download PDF

30. COVID-19 Exacerbates Neurovascular Uncoupling and Contributes to Endothelial Dysfunction in Patients with Mild Cognitive Impairment

Author

Cameron D. Owens, Camila B. Pinto, Zsofia Szarvas, Mihaly Muranyi, Ana Clara da C. Pinaffi-Langley, Anna Peterfi, Peter Mukli, Sam Detwiler, Lauren Olay, Zalan Kaposzta, Kenneth Smith, Angelia C. Kirkpatrick, Faddi Saleh Velez, Stefano Tarantini, Anna Csiszar, Zoltan I. Ungvari, Calin I. Prodan, and Andriy Yabluchanskiy

Subjects
mild cognitive impairment, neurovascular coupling, COVID-19, endothelial function, flow-mediated dilation, Microbiology, QR1-502
Abstract

Mild cognitive impairment (MCI) affects nearly 20% of older adults worldwide, with no targetable interventions for prevention. COVID-19 adversely affects cognition, with >70% of older adults with Long COVID presenting with cognitive complaints. Neurovascular coupling (NVC), an essential mechanism of cognitive function, declines with aging and is further attenuated in neurocognitive disorders. The effect of COVID-19 on NVC responses has yet to be addressed in older adults who are vulnerable to dementia progression. Participants with MCI and a history of COVID-19 (COV+, N = 31) and MCI participants with no history of infection (COV− N = 11) participated in this cross-sectional study to determine if COVID-19 affects cerebrocortical NVC responses and vascular function. Functional near-infrared spectroscopy was used to measure cerebrocortical NVC responses, and endothelial function was assessed via insonation of the brachial artery during a flow-mediated dilation protocol. NVC responses were elicited by the working memory n-back paradigm. NVC in the left dorsolateral prefrontal cortex and endothelial function was decreased in the COV+ group compared to the COV− group. These data provide mechanistic insight into how COVID-19 may exacerbate long-term cognitive sequela seen in older adults, highlighting the urgent need for further research and clinical trials to explore novel therapeutic interventions aimed at preserving/restoring NVC.

Published
2024
Full Text
View/download PDF

31. Squashing activation functions in benchmark tests: towards eXplainable Artificial Intelligence using continuous-valued logic

Author

Zeltner, Daniel, Schmid, Benedikt, Csiszar, Gabor, and Csiszar, Orsolya

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Over the past few years, deep neural networks have shown excellent results in multiple tasks, however, there is still an increasing need to address the problem of interpretability to improve model transparency, performance, and safety. Achieving eXplainable Artificial Intelligence (XAI) by combining neural networks with continuous logic and multi-criteria decision-making tools is one of the most promising ways to approach this problem: by this combination, the black-box nature of neural models can be reduced. The continuous logic-based neural model uses so-called Squashing activation functions, a parametric family of functions that satisfy natural invariance requirements and contain rectified linear units as a particular case. This work demonstrates the first benchmark tests that measure the performance of Squashing functions in neural networks. Three experiments were carried out to examine their usability and a comparison with the most popular activation functions was made for five different network types. The performance was determined by measuring the accuracy, loss, and time per epoch. These experiments and the conducted benchmarks have proven that the use of Squashing functions is possible and similar in performance to conventional activation functions. Moreover, a further experiment was conducted by implementing nilpotent logical gates to demonstrate how simple classification tasks can be solved successfully and with high performance. The results indicate that due to the embedded nilpotent logical operators and the differentiability of the Squashing function, it is possible to solve classification problems, where other commonly used activation functions fail.

Published
2020

33. Obesity and Cognitive Decline

Author

Tabak, Adam, primary, Fazekas-Pongor, Vince, additional, Tarantini, Stefano, additional, Balasubramanian, Priya, additional, Csiszar, Anna, additional, and Ungvari, Zoltan, additional

Published
2024
Full Text
View/download PDF

34. Parametric Activation Functions for Neural Networks: A Tutorial Survey

Author

Luca Sara Pusztahazi, Gyorgy Eigner, and Orsolya Csiszar

Subjects
Parametric activation functions, neural networks, fuzzy neural networks, learnable activation functions, Kolmogorov-Arnold networks (KAN), Electrical engineering. Electronics. Nuclear engineering, TK1-9971
Abstract

Activation functions are pivotal in neural networks, determining the output of each neuron. Traditionally, functions like sigmoid and ReLU have been static and deterministic. However, the introduction of parametric activation functions represents a significant paradigm shift by incorporating adjustable parameters, thus enhancing flexibility and optimization capabilities. Furthermore, parametric activation functions can enhance interpretability, helping to solve the black-box problem and providing deeper insights into the functioning of neural networks. They are also essential components of the innovative model of Kolmogorov-Arnold Network, that features learnable activation functions on the edges of the neural network. This review highlights the importance, characteristics, and applications of these parametric functions in neural networks. Notable examples of parametric activation functions are analyzed, with emphasis on their mathematical formulations and their transformative impact on modern neural networks. These functions not only represent an evolutionary step but a substantial shift in the design and optimization of neural network architectures, offering a promising avenue for innovation and advancement in the field.

Published
2024
Full Text
View/download PDF

35. Elimination of senescent cells by treatment with Navitoclax/ABT263 reverses whole brain irradiation-induced blood-brain barrier disruption in the mouse brain

Author

Gulej, Rafal, Nyúl-Tóth, Ádám, Ahire, Chetan, DelFavero, Jordan, Balasubramanian, Priya, Kiss, Tamas, Tarantini, Stefano, Benyo, Zoltan, Pacher, Pal, Csik, Boglarka, Yabluchanskiy, Andriy, Mukli, Peter, Kuan-Celarier, Anna, Krizbai, István A, Campisi, Judith, Sonntag, William E., Csiszar, Anna, and Ungvari, Zoltan

Published
2023
Full Text
View/download PDF

39. Expanding the horizon of research into the pathogenesis of the white matter diseases: Proceedings of the 2021 Annual Workshop of the Albert Research Institute for White Matter and Cognition.

Author

Whitehead, Shawn N, Bruno, Askiel, Burns, Jeffrey M, Carmichael, S Thomas, Csiszar, Anna, Edwards, Jodi D, Elahi, Fanny M, Faraco, Giuseppe, Gould, Douglas B, Gustafson, Deborah R, Hachinski, Vladimir, Rosenberg, Gary, Sorond, Farzaneh A, Shih, Andy Y, Tse, Kai Hei, Ungvari, Zoltan, Wilcock, Donna M, Zuloaga, Kristen L, and Barone, Frank C

Subjects
Humans, Dementia, Vascular, Cognition, Academies and Institutes, Leukoencephalopathies, White Matter, AD, Neurodegenerative disease/injury, VCID, White matter, Acquired Cognitive Impairment, Behavioral and Social Science, Neurodegenerative, Alzheimer's Disease, Alzheimer's Disease including Alzheimer's Disease Related Dementias (AD/ADRD), Neurosciences, Prevention, Dementia, Brain Disorders, Aging, Neurological, Good Health and Well Being, Neurodegenerative disease, injury
Abstract

White matter pathologies are critically involved in the etiology of vascular cognitive impairment-dementia (VCID), Alzheimer's disease (AD), and Alzheimer's disease and related diseases (ADRD), and therefore need to be considered a treatable target ( Roseborough A, Hachinski V, Whitehead S. White matter degeneration - a treatable target? Roseborough et al. JAMA Neurol [Internet]. 2020 Apr 27;77(7):793-4, [1] . To help address this often-missed area of research, several workshops have been sponsored by the Leo and Anne Albert Charitable Trust since 2015, resulting in the incorporation of "The Albert Research Institute for White Matter and Cognition" in 2020. The first annual "Institute" meeting was held virtually on March 3-4, 2021. The Institute provides a forum and workspace for communication and support of the advancement of white matter science and research to better understand the evolution and prevention of dementia. It serves as a platform for young investigator development, to introduce new data and debate biology mechanisms and new ideas, and to encourage and support new research collaborations and directions to clarify how white matter changes, with other genetic and health risk factors, contribute to cognitive impairment. Similar to previous Albert Trust-sponsored workshops (Barone et al. in J Transl Med 14:1-14, [2]; Sorond et al. in GeroScience 42:81-96, [3]), established expert investigators were identified and invited to present. Opportunities to attend and present were also extended by invitation to talented research fellows and younger scientists. Also, updates on institute-funded research collaborations were provided and discussed. The summary that follows is a synopsis of topics and discussion covered in the workshop.

Published
2022

45. Interpretable neural networks based on continuous-valued logic and multicriteria decision operators

Author

Csiszár, Orsolya, Csiszár, Gábor, and Dombi, József

Subjects
Computer Science - Artificial Intelligence
Abstract

Combining neural networks with continuous logic and multicriteria decision making tools can reduce the black box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathematical framework for a hybridization of continuous nilpotent logic and neural models, helping to improve the interpretability and safety of machine learning. In our concept, perceptrons model soft inequalities; namely membership functions and continuous logical operators. We design the network architecture before training, using continuous logical operators and multicriteria decision tools with given weights working in the hidden layers. Designing the structure appropriately leads to a drastic reduction in the number of parameters to be learned. The theoretical basis offers a straightforward choice of activation functions (the cutting function or its differentiable approximation, the squashing function), and also suggests an explanation to the great success of the rectified linear unit (ReLU). In this study, we focus on the architecture of a hybrid model and introduce the building blocks for future application in deep neural networks. The concept is illustrated with some toy examples taken from an extended version of the tensorflow playground.

Published
2019
Full Text
View/download PDF

46. Measurements of cerebral microvascular blood flow, oxygenation, and morphology in a mouse model of whole-brain irradiation-induced cognitive impairment by two-photon microscopy and optical coherence tomography: evidence for microvascular injury in the cerebral white matter

Author

Li, Baoqiang, Yabluchanskiy, Andriy, Tarantini, Stefano, Allu, Srinivasa Rao, Şencan-Eğilmez, Ikbal, Leng, Ji, Alfadhel, Mohammed Ali H., Porter, Jason E., Fu, Buyin, Ran, Chongzhao, Erdener, Sefik Evren, Boas, David A., Vinogradov, Sergei A., Sonntag, William E., Csiszar, Anna, Ungvari, Zoltan, and Sakadžić, Sava

Published
2023
Full Text
View/download PDF

47. Impaired Neurovascular Coupling and Increased Functional Connectivity in the Frontal Cortex Predict Age‐Related Cognitive Dysfunction

Author

Peter Mukli, Camila B. Pinto, Cameron D. Owens, Tamas Csipo, Agnes Lipecz, Zsofia Szarvas, Anna Peterfi, Ana Clara da Costa Pinaffi Langley, Jordan Hoffmeister, Frigyes Samuel Racz, Jonathan W. Perry, Stefano Tarantini, Ádám Nyúl‐Tóth, Farzaneh A. Sorond, Yuan Yang, Judith A. James, Angelia C. Kirkpatrick, Calin I. Prodan, Peter Toth, Juliette Galindo, Andrew W. Gardner, William E. Sonntag, Anna Csiszar, Zoltan Ungvari, and Andriy Yabluchanskiy

Subjects
aging, cognitive decline, functional connectivity, functional near‐infrared spectroscopy, neurovascular coupling, Science
Abstract

Abstract Impaired cerebrovascular function contributes to the genesis of age‐related cognitive decline. In this study, the hypothesis is tested that impairments in neurovascular coupling (NVC) responses and brain network function predict cognitive dysfunction in older adults. Cerebromicrovascular and working memory function of healthy young (n = 21, 33.2±7.0 years) and aged (n = 30, 75.9±6.9 years) participants are assessed. To determine NVC responses and functional connectivity (FC) during a working memory (n‐back) paradigm, oxy‐ and deoxyhemoglobin concentration changes from the frontal cortex using functional near‐infrared spectroscopy are recorded. NVC responses are significantly impaired during the 2‐back task in aged participants, while the frontal networks are characterized by higher local and global connection strength, and dynamic FC (p < 0.05). Both impaired NVC and increased FC correlate with age‐related decline in accuracy during the 2‐back task. These findings suggest that task‐related brain states in older adults require stronger functional connections to compensate for the attenuated NVC responses associated with working memory load.

Published
2024
Full Text
View/download PDF

48. Deep Reinforcement Learning using Cyclical Learning Rates

Author

Gulde, Ralf, Tuscher, Marc, Csiszar, Akos, Riedel, Oliver, and Verl, Alexander

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Deep Reinforcement Learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gradient descent (SGD) is the learning rate. We investigate cyclical learning and propose a method for defining a general cyclical learning rate for various DRL problems. In this paper we present a method for cyclical learning applied to complex DRL problems. Our experiments show that, utilizing cyclical learning achieves similar or even better results than highly tuned fixed learning rates. This paper presents the first application of cyclical learning rates in DRL settings and is a step towards overcoming manual hyperparameter tuning.

Published
2020

49. Reinforcement Learning Approach to Vibration Compensation for Dynamic Feed Drive Systems

Author

Gulde, Ralf, Tuscher, Marc, Csiszar, Akos, Riedel, Oliver, and Verl, Alexander

Subjects
Electrical Engineering and Systems Science - Systems and Control, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

Vibration compensation is important for many domains. For the machine tool industry it translates to higher machining precision and longer component lifetime. Current methods for vibration damping have their shortcomings (e.g. need for accurate dynamic models). In this paper we present a reinforcement learning based approach to vibration compensation applied to a machine tool axis. The work describes the problem formulation, the solution, the implementation and experiments using industrial machine tool hardware and control system.

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results