Marios Thoma has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Quality Diversity as a Decision Support Tool for Digital Asset Portfolio Management

    by Marios Thoma, Giorgos Demosthenous, Vassilis Vassiliades

    Portfolio managers navigating digital asset markets require more than a single optimal solution; they need structured visibility into the landscape of high-quality alternatives. We introduce a hierarchical Quality Diversity framework that discovers and organizes thousands of diverse, high-performing portfolios across risk-return profiles. Although high-dimensional archives can capture this complexity, they lack the structure necessary for practical decision-making. Our two-level archive prioritizes concentration and volatility at the top level while preserving category allocation diversity within each risk bracket, enabling practitioners to select a risk profile first, then choose among compositional strategies within that bracket. Across 33 digital assets spanning 14 categories, we demonstrate that meaningful diversification is achievable under low-to-moderate volatility regimes, while high-volatility portfolios remain necessarily concentrated due to strong correlation structures. Beyond portfolio discovery, the archive structure enables transaction-cost-aware rebalancing by providing performance improvements at varying proximity to existing allocations, allowing practitioners to balance fitness gains against operational constraints.

  • Open Access

    Neural-Symbolic Integration with Evolvable Policies

    by Marios Thoma, Vassilis Vassiliades, Loizos Michael

    Neural-Symbolic (NeSy) Artificial Intelligence has emerged as a promising approach for combining the learning capabilities of neural networks with the interpretable reasoning of symbolic systems. However, existing NeSy frameworks typically require either predefined symbolic policies or policies that are differentiable, limiting their applicability when domain expertise is unavailable or when policies are inherently non-differentiable. We propose a framework that addresses this limitation by enabling the concurrent learning of both non-differentiable symbolic policies and neural network weights through an evolutionary process. Our approach casts NeSy systems as organisms in a population that evolve through mutations (both symbolic rule additions and neural weight changes), with fitness-based selection guiding convergence toward hidden target policies. The framework extends the NEUROLOG architecture to make symbolic policies trainable, adapts Valiant's Evolvability framework to the NeSy context, and employs Machine Coaching semantics for mutable symbolic representations. Neural networks are trained through abductive reasoning from the symbolic component, eliminating differentiability requirements. Through extensive experimentation, we demonstrate that NeSy systems starting with empty policies and random neural weights can successfully approximate hidden non-differentiable target policies, achieving median correct performance approaching 100%. This work represents a step toward enabling NeSy research in domains where the acquisition of symbolic knowledge from experts is challenging or infeasible.

  • Open Access

    PEDESTRIAN: An Egocentric Vision Dataset for Obstacle Detection on Pavements

    by Marios Thoma, Zenonas Theodosiou, Harris Partaourides, Vassilis Vassiliades, Loizos Michael, Andreas Lanitis

    Walking has always been a primary mode of transportation and is recognized as an essential activity for maintaining good health. Despite the need for safe walking conditions in urban environments, sidewalks are frequently obstructed by various obstacles that hinder free pedestrian movement. Any object obstructing a pedestrian's path can pose a safety hazard. The advancement of pervasive computing and egocentric vision techniques offers the potential to design systems that can automatically detect such obstacles in real time, thereby enhancing pedestrian safety. The development of effective and efficient identification algorithms relies on the availability of comprehensive and well-balanced datasets of egocentric data. In this work, we introduce the PEDESTRIAN dataset, comprising egocentric data for 29 different obstacles commonly found on urban sidewalks. A total of 340 videos were collected using mobile phone cameras, capturing a pedestrian's point of view. Additionally, we present the results of a series of experiments that involved training several state-of-the-art deep learning algorithms using the proposed dataset, which can be used as a benchmark for obstacle detection and recognition tasks. The dataset can be used for training pavement obstacle detectors to enhance the safety of pedestrians in urban areas.

  • Performance Assessment of Fine-Tuned Barrier Recognition Models in Varying Conditions

    by Marios Thoma, Harris Partaourides, Ieswaria Sreedharan, Zenonas Theodosiou, Loizos Michael, Andreas Lanitis


  • Open Access

    A Systematic Approach for Developing a Robust Artwork Recognition Framework Using Smartphone Cameras

    by Zenonas Theodosiou, Marios Thoma, Harris Partaourides, Andreas Lanitis

    The provision of information encourages people to visit cultural sites more often. Exploiting the great potential of using smartphone cameras and egocentric vision, we describe the development of a robust artwork recognition algorithm to assist users when visiting an art space. The algorithm recognizes artworks under any physical museum conditions, as well as camera point of views, making it suitable for different use scenarios towards an enhanced visiting experience. The algorithm was developed following a multiphase approach, including requirements gathering, experimentation in a virtual environment, development of the algorithm in real environment conditions, implementation of a demonstration smartphone app for artwork recognition and provision of assistive information, and its evaluation. During the algorithm development process, a convolutional neural network (CNN) model was trained for automatic artwork recognition using data collected in an art gallery, followed by extensive evaluations related to the parameters that may affect recognition accuracy, while the optimized algorithm was also evaluated through a dedicated app by a group of volunteers with promising results. The overall algorithm design and evaluation adopted for this work can also be applied in numerous applications, especially in cases where the algorithm performance under varying conditions and end-user satisfaction are critical factors.