Vasileios Maroulas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Vasileios Maroulas has a total of 101 co-authors. Here are the top co-authors by number of shared publications:
- Konstantinos D. Vogiatzis
Department of Chemistry University of Tennessee Knoxville Tennessee USA
5 shared publications Jacob Townsend
Department of Chemistry, University of Tennessee, Knoxville, USA
4 shared publications- Adam Spannaus
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
3 shared publications Cassie Putman Micucci
3 shared publications- Cassie Putman Micucci
Department of Mathematics, University of Tennessee, Knoxville, USA
3 shared publications - David J. Keffer
Department of Materials Science and Engineering, University of Tennessee, Knoxville, TN 37996, USA
3 shared publications
Latest Publications
- Open Access
- 23 April 2026
- Published by Elsevier in Informatics in Medicine Unlocked
- Vol. 63
Investigating the opioid epidemic across the United States: Associations between county-level characteristics and overdose mortality
- 23 April 2026
- Published by Elsevier in Informatics in Medicine Unlocked
- Vol. 63
Open AccessInvestigating the opioid epidemic across the United States: Associations between county-level characteristics and overdose mortality
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in Foundations of Data Science
Bayesian topological convolutional neural nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important manifolds to accelerate training while reducing calibration error by placing prior distributions on network parameters and properly learning appropriate posteriors. One important contribution of our work is the inclusion of a consistency condition in the learning cost, which can effectively modify the prior distributions to improve the performance of our novel network architecture. We evaluate the model on benchmark image classification datasets and demonstrate its superiority over conventional CNNs, Bayesian neural networks (BNNs), and topological CNNs. In particular, we supply evidence that our method provides an advantage in situations where training data is limited or corrupted. Furthermore, we show that the new model allows for better uncertainty quantification than standard BNNs since it can more readily identify examples of out-of-distribution data on which it has not been trained. Our results highlight the potential of our novel hybrid approach for more efficient and robust image classification.
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in Foundations of Data Science
Bayesian topological convolutional neural nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important manifolds to accelerate training while reducing calibration error by placing prior distributions on network parameters and properly learning appropriate posteriors. One important contribution of our work is the inclusion of a consistency condition in the learning cost, which can effectively modify the prior distributions to improve the performance of our novel network architecture. We evaluate the model on benchmark image classification datasets and demonstrate its superiority over conventional CNNs, Bayesian neural networks (BNNs), and topological CNNs. In particular, we supply evidence that our method provides an advantage in situations where training data is limited or corrupted. Furthermore, we show that the new model allows for better uncertainty quantification than standard BNNs since it can more readily identify examples of out-of-distribution data on which it has not been trained. Our results highlight the potential of our novel hybrid approach for more efficient and robust image classification.
- Top Cited PapersOpen Access
- 21 December 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (2)
Topological data analysis and topological deep learning beyond persistent homology: a review
Topological data analysis (TDA) is a rapidly evolving field in applied mathematics and data science that leverages tools from topology to uncover robust, shape-driven, and explainable insights in complex datasets. The main workhorse is persistent homology, a technique rooted in algebraic topology. Paired with topological deep learning (TDL) or topological machine learning, persistent homology has achieved tremendous success in a wide variety of applications in science, engineering, medicine, and industry. However, persistent homology has many limitations due to its high-level abstraction, insensitivity to non-topological changes, and restriction to point cloud data. This paper presents a comprehensive review of TDA and TDL beyond persistent homology. It analyzes how persistent topological Laplacians and Dirac operators provide spectral representations to capture both topological invariants and homotopic evolution. Other formulations are presented in terms of sheaf theory, Mayer topology, and interaction topology. For data on differentiable manifolds, techniques rooted in differential topology, such as persistent de Rham cohomology, persistent Hodge Laplacian, and Hodge decomposition, are reviewed. For one-dimensional (1D) curves embedded in 3-space, approaches from geometric topology are discussed, including multiscale Gauss-link integrals, persistent Jones polynomials, and persistent Khovanov homology. This paper further discusses the appropriate selection of topological tools for different input data, such as point clouds, sequential data, data on manifolds, curves embedded in 3-space, and data with additional non-geometric information. A review is also given of various topological representations, software packages, and machine learning vectorizations. Finally, this review ends with concluding remarks.
- 21 December 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (2)
Top Cited PapersOpen AccessTopological data analysis and topological deep learning beyond persistent homology: a review
Topological data analysis (TDA) is a rapidly evolving field in applied mathematics and data science that leverages tools from topology to uncover robust, shape-driven, and explainable insights in complex datasets. The main workhorse is persistent homology, a technique rooted in algebraic topology. Paired with topological deep learning (TDL) or topological machine learning, persistent homology has achieved tremendous success in a wide variety of applications in science, engineering, medicine, and industry. However, persistent homology has many limitations due to its high-level abstraction, insensitivity to non-topological changes, and restriction to point cloud data. This paper presents a comprehensive review of TDA and TDL beyond persistent homology. It analyzes how persistent topological Laplacians and Dirac operators provide spectral representations to capture both topological invariants and homotopic evolution. Other formulations are presented in terms of sheaf theory, Mayer topology, and interaction topology. For data on differentiable manifolds, techniques rooted in differential topology, such as persistent de Rham cohomology, persistent Hodge Laplacian, and Hodge decomposition, are reviewed. For one-dimensional (1D) curves embedded in 3-space, approaches from geometric topology are discussed, including multiscale Gauss-link integrals, persistent Jones polynomials, and persistent Khovanov homology. This paper further discusses the appropriate selection of topological tools for different input data, such as point clouds, sequential data, data on manifolds, curves embedded in 3-space, and data with additional non-geometric information. A review is also given of various topological representations, software packages, and machine learning vectorizations. Finally, this review ends with concluding remarks.
- Open Access
Bayesian Topological Convolutional Neural Nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important manifolds to accelerate training while reducing calibration error by placing prior distributions on network parameters and properly learning appropriate posteriors. One important contribution of our work is the inclusion of a consistency condition in the learning cost, which can effectively modify the prior distributions to improve the performance of our novel network architecture. We evaluate the model on benchmark image classification datasets and demonstrate its superiority over conventional CNNs, Bayesian neural networks (BNNs), and topological CNNs. In particular, we supply evidence that our method provides an advantage in situations where training data is limited or corrupted. Furthermore, we show that the new model allows for better uncertainty quantification than standard BNNs since it can more readily identify examples of out-of-distribution data on which it has not been trained. Our results highlight the potential of our novel hybrid approach for more efficient and robust image classification.
Open AccessBayesian Topological Convolutional Neural Nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important manifolds to accelerate training while reducing calibration error by placing prior distributions on network parameters and properly learning appropriate posteriors. One important contribution of our work is the inclusion of a consistency condition in the learning cost, which can effectively modify the prior distributions to improve the performance of our novel network architecture. We evaluate the model on benchmark image classification datasets and demonstrate its superiority over conventional CNNs, Bayesian neural networks (BNNs), and topological CNNs. In particular, we supply evidence that our method provides an advantage in situations where training data is limited or corrupted. Furthermore, we show that the new model allows for better uncertainty quantification than standard BNNs since it can more readily identify examples of out-of-distribution data on which it has not been trained. Our results highlight the potential of our novel hybrid approach for more efficient and robust image classification.
- Open Access
- 10 September 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
Functional ultrasound imaging combined with machine learning for whole-brain analysis of drug-induced hemodynamic changes
Functional ultrasound imaging (fUSI) is a cutting-edge technology that measures changes in cerebral blood volume (CBV) by detecting backscattered echoes from red blood cells moving within its field of view (FOV). It offers high spatiotemporal resolution and sensitivity, allowing for detailed visualization of cerebral blood flow dynamics. While fUSI has been utilized in preclinical drug development studies to explore the mechanisms of action of various drugs targeting the central nervous system, many of these studies rely on predetermined regions of interest (ROIs). This focus may overlook relevant brain activity outside these specific areas, which could influence the results. To address this limitation, we compared three machine learning approaches—convolutional neural network (CNN), support vector machine (SVM), and vision transformer (ViT)—combined with fUSI to analyze the pharmacodynamics of dizocilpine (MK-801), a potent non-competitive NMDA receptor antagonist commonly used in preclinical models for memory and learning impairments. While all three machine learning techniques could distinguish between drug and control conditions, CNN proved particularly effective due to its ability to capture hierarchical spatial features while maintaining anatomical specificity. Class activation mapping revealed brain regions, including the prefrontal cortex and hippocampus, that are significantly affected by drug administration, consistent with literature reporting a high density of NMDA receptors in these areas. Overall, the combination of fUSI and CNN creates a novel analytical framework for examining pharmacological mechanisms, allowing for data-driven identification and regional mapping of drug effects while preserving anatomical context and physiological relevance.
- 10 September 2025
- Published by MIT Press in Imaging Neuroscience
- Vol. 3
Open AccessFunctional ultrasound imaging combined with machine learning for whole-brain analysis of drug-induced hemodynamic changes
Functional ultrasound imaging (fUSI) is a cutting-edge technology that measures changes in cerebral blood volume (CBV) by detecting backscattered echoes from red blood cells moving within its field of view (FOV). It offers high spatiotemporal resolution and sensitivity, allowing for detailed visualization of cerebral blood flow dynamics. While fUSI has been utilized in preclinical drug development studies to explore the mechanisms of action of various drugs targeting the central nervous system, many of these studies rely on predetermined regions of interest (ROIs). This focus may overlook relevant brain activity outside these specific areas, which could influence the results. To address this limitation, we compared three machine learning approaches—convolutional neural network (CNN), support vector machine (SVM), and vision transformer (ViT)—combined with fUSI to analyze the pharmacodynamics of dizocilpine (MK-801), a potent non-competitive NMDA receptor antagonist commonly used in preclinical models for memory and learning impairments. While all three machine learning techniques could distinguish between drug and control conditions, CNN proved particularly effective due to its ability to capture hierarchical spatial features while maintaining anatomical specificity. Class activation mapping revealed brain regions, including the prefrontal cortex and hippocampus, that are significantly affected by drug administration, consistent with literature reporting a high density of NMDA receptors in these areas. Overall, the combination of fUSI and CNN creates a novel analytical framework for examining pharmacological mechanisms, allowing for data-driven identification and regional mapping of drug effects while preserving anatomical context and physiological relevance.
- Open Access
- 4 August 2025
- Published by Springer Nature in npj Artificial Intelligence
- Vol. 1 (1) , 1-10
Geometric sparsification in recurrent neural networks
- 4 August 2025
- Published by Springer Nature in npj Artificial Intelligence
- Vol. 1 (1) , 1-10
Open AccessGeometric sparsification in recurrent neural networks
- Open Access
- 23 January 2025
- Published by IOP Publishing in Journal of Physics: Complexity
- Vol. 6 (1) , 015005
Quantum distance approximation for persistence diagrams
Topological data analysis (TDA) methods can be useful for classification and clustering tasks in many different fields as they can provide two dimensional persistence diagrams that summarize important information about the shape of potentially complex and high dimensional data sets. The space of persistence diagrams can be endowed with various metrics, which admit a statistical structure and allow to use these summaries for machine learning algorithms, e.g. the Wasserstein distance. However, computing the distance between two persistence diagrams involves finding an optimal way to match the points of the two diagrams and may not always be an easy task for classical computers. Recently, quantum algorithms have shown the potential to speedup the process of obtaining the persistence information displayed on persistence diagrams by estimating the spectra of persistent Dirac operators. So, in this work we explore the potential of quantum computers to estimate the distance between persistence diagrams as the next step in the design of a fully quantum framework for TDA. In particular we propose variational quantum algorithms for the Wasserstein distance as well as the d p c distance. Our implementation is a weighted version of the quantum approximate optimization Algorithm that relies on control clauses to encode the constraints of the optimization problem.
- 23 January 2025
- Published by IOP Publishing in Journal of Physics: Complexity
- Vol. 6 (1) , 015005
Open AccessQuantum distance approximation for persistence diagrams
Topological data analysis (TDA) methods can be useful for classification and clustering tasks in many different fields as they can provide two dimensional persistence diagrams that summarize important information about the shape of potentially complex and high dimensional data sets. The space of persistence diagrams can be endowed with various metrics, which admit a statistical structure and allow to use these summaries for machine learning algorithms, e.g. the Wasserstein distance. However, computing the distance between two persistence diagrams involves finding an optimal way to match the points of the two diagrams and may not always be an easy task for classical computers. Recently, quantum algorithms have shown the potential to speedup the process of obtaining the persistence information displayed on persistence diagrams by estimating the spectra of persistent Dirac operators. So, in this work we explore the potential of quantum computers to estimate the distance between persistence diagrams as the next step in the design of a fully quantum framework for TDA. In particular we propose variational quantum algorithms for the Wasserstein distance as well as the d p c distance. Our implementation is a weighted version of the quantum approximate optimization Algorithm that relies on control clauses to encode the constraints of the optimization problem.
- 22 February 2024
- Published by Elsevier in Biophysical Journal
- Vol. 123 (17) , 2781-2789
A topological deep learning framework for neural spike decoding
- 22 February 2024
- Published by Elsevier in Biophysical Journal
- Vol. 123 (17) , 2781-2789
A topological deep learning framework for neural spike decoding
- Top Cited Papers
- 31 January 2024
- Published by Springer Nature in Journal of Applied and Computational Topology
- Vol. 8 (7) , 1961-1980
Quantum persistent homology
- 31 January 2024
- Published by Springer Nature in Journal of Applied and Computational Topology
- Vol. 8 (7) , 1961-1980
Top Cited PapersQuantum persistent homology
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Foundations of Data Science
- Vol. 6 (3) , 361-378
Bayesian random persistence diagram generation: An application to material microstructure analysis
Data analysis helps identify changes in the microstructure of materials, but is often hindered by the cost and time requirements of experimental data generation. Data augmentation provides an in silico alternative. A recent data augmentation algorithm, known as the random persistence diagram generator (RPDG), samples a sequence of synthetic topological summaries from a possibly limited amount of data. RPDG relies on a parametric model for persistence diagrams, namely a pairwise interacting point process (PIPP). Herein, we develop a Bayesian approach to infer the PIPP parameters and call the resulting pipeline the Bayesian RPDG (BRPDG). We showcase that BRPDG exhibits higher discriminative power than RPDG in the identification of materials structural changes.
- 1 January 2024
- Published by American Institute of Mathematical Sciences (AIMS) in Foundations of Data Science
- Vol. 6 (3) , 361-378
Bayesian random persistence diagram generation: An application to material microstructure analysis
Data analysis helps identify changes in the microstructure of materials, but is often hindered by the cost and time requirements of experimental data generation. Data augmentation provides an in silico alternative. A recent data augmentation algorithm, known as the random persistence diagram generator (RPDG), samples a sequence of synthetic topological summaries from a possibly limited amount of data. RPDG relies on a parametric model for persistence diagrams, namely a pairwise interacting point process (PIPP). Herein, we develop a Bayesian approach to infer the PIPP parameters and call the resulting pipeline the Bayesian RPDG (BRPDG). We showcase that BRPDG exhibits higher discriminative power than RPDG in the identification of materials structural changes.