1,720,992 research outputs found
Theory-guided Data Science models
Full text linkL'abstract è presente nell'allegato / the abstract is in the attachmen
Experimental Comparison of Theory-Guided Deep Learning Algorithms
No full textThe enrichment of machine learning models with domain knowledge has a growing impact on modern engineering and physics problems. This trend stems from the fact that the rise of deep learning algorithms is closely associated with an increasing demand for data that is not acceptable or available in many use cases. In this context, the incorporation of physical knowledge or a-priori constraints has been shown to be beneficial in many tasks. On the other hand, this collection of approaches is context-specific, and it is difficult to generalize them to new problems. In this paper, we experimentally compare some of the most widely used theory injection strategies to perform a systematic analysis of their advantages. Selected state-of-the-art algorithms have been reproduced for different use cases to evaluate their effectiveness with smaller training data and to discuss how the underlined strategies can fit into new application contexts
Lorentz-invariant augmentation for high-energy physics
No full textIn recent years, machine learning models for jet tagging in high-energy physics have gained considerable attention. However, many existing approaches overlook the physical invariants that jets must adhere to, particularly the fundamental spacetime symmetry governed by Lorentz transformations.
In this study, we propose a model-agnostic training strategy that incorporates theory-guided data augmentation to simulate the effects of Lorentz transformations on jet data. We specifically focus on the state-of-the-art baseline ParticleNet, a neural network architecture designed for the direct processing of particle clouds for jet tagging. To evaluate the effectiveness of our approach, we conduct experiments with different augmentation strategies and assess the performance of the augmented models on the widely used top-tagging reference dataset.
The results show that even a small application of the data augmentation strategy increases the robustness of the model to Lorentz boost attacks, i.e., high transformation β.
While the accuracy of the baseline model decreases rapidly with increasing intensity of the transformation β, the augmented models exhibit more stable performance.
Remarkably, models that underwent a moderate level of augmentation demonstrated a statistically significant performance boost on transformations beyond the ones seen at train time. This finding highlights the potential of the data augmentation strategy in enhancing model accuracy while preserving the essential physical properties of the jets
A Comparative Study of Neural Ordinary Differential Equations and Neural Operators for Modeling Temporal Dynamics
Full text linkCapturing the dynamics of relational systems is a key challenge in the natural sciences, with applications ranging from simulating molecular interactions to analyzing particle mechanics. Machine learning approaches have made significant progress in this area by using graph neural networks to learn and visualize spatial interactions effectively. Neural ordinary differential equations (Neural ODEs) and neural operators (NO) represent two distinct paradigms. However, a clear comparative understanding of when to prefer one over the other is still lacking. To address this gap, we present the first systematic comparison between two representative architectures: EGNO (Equivariant Graph Neural Operator) and SEGNO (Second-order Equivariant Graph Neural Ordinary Differential Equation). Through a series of experiments, we investigate their strengths and limitations in various simulation scenarios in the multi-step trajectory prediction tasks. Specifically, we employ rollout strategies and different input/output configurations, including multiple and irregularly sampled time steps. Our findings highlight a key trade-off between precision and stability that is central to model selection. SEGNO demonstrates superior robustness and stability over long prediction horizons, making it well-suited for tasks requiring reliable long-term forecasting. Conversely, EGNO offers higher precision during early stages of the trajectory and better leverages diverse training configurations, thanks to its discretization-invariant design. In summary, Neural Operators (EGNO) are preferable when short-term accuracy and data efficiency are critical, while Neural ODEs (SEGNO) are advantageous for scenarios demanding stable long-term predictions. This work not only clarifies the practical advantages of each approach but also lays the groundwork for informed model selection and future hybrid strategies in dynamical system modeling
Prediction of coffee consumption using Graph Neural Networks and Explainable AI
No full textAccurate forecasting regional sales in heterogeneous locations presents a complex challenge that extends beyond the capabilities of traditional predictive models. In this study, we focus on predicting coffee sales for one of the local coffee companies in Italy by integrating machine learning techniques with graph-based deep learning models. We begin by establishing a baseline using a Multi-Layer Perceptron (MLP) and subsequently apply six Graph Neural Network (GNN) architectures: GCN, GAT, GraphSAGE, GIN, ChebNet, and GraphConv to capture spatial dependencies among distribution points. To enhance model interpretability and guide feature selection, we incorporate Integrated Gradients from the Explainable AI (XAI) framework. Experimental results demonstrate that GNNs consistently outperform the MLP baseline, particularly in capturing location-driven relational patterns. In particular, the results show how GraphSAGE and ChebNet outperformed the other architectures. The integration of graph-based modeling with interpretable learning provides valuable insights for optimizing sales strategies in geographically distributed markets
Uncertainty-aware methods for enhancing rainfall prediction with deep-learning based post-processing segmentation
Full text linkPrecipitation forecast is critical in flood management, agricultural planning, water resource allocation, and weather warnings. Despite significant advancements in Numerical Weather Prediction (NWP) models, these systems often exhibit substantial biases and errors, particularly at high spatial and temporal resolutions. To address these limitations, we develop and evaluate uncertainty-aware deep learning ensemble architectures, focusing on characterizing forecast uncertainties while achieving high accuracy and an optimal balance between sharpness and reliability. This study presents SDE U-Net, a novel adaptation of SDE-Net designed specifically for segmentation tasks in precipitation forecasting. We conduct a comprehensive evaluation of state-of-the-art ensemble architectures, including SDE U-Net, and compare their forecast uncertainty against that of a Poor Man's Ensemble (PME, i.e. NWPs forecast average) across diverse meteorological conditions, ranging from non-intense precipitation patterns to intense weather events. As an example case, we focus on predicting daily cumulative precipitation in northwest Italy, though our approach is broadly generalizable. Our findings demonstrate that all the evaluated probabilistic deep learning models outperform the PME benchmark in terms of median RMSE for both non-intense and intense precipitation events. Among them, SDE U-Net achieves the best overall performance, delivering the lowest RMSE for intense events (2.637 * 10-2) and demonstrating a more stable error distribution compared to other models. For non-intense events, SDE U-Net perform comparably to other deep learning models, still notably surpassing the baselines. Moreover, SDE U-Net effectively balances sharpness and reliability, making it particularly suitable for operational forecasting of extreme weather. Integrating uncertainty-aware models like SDE U-Net into forecasting workflows can enhance decision-making and preparedness for weather-related hazards
Quantify production planning efficiency through predictive modeling in manufacturing systems
Full text linkThis paper proposes a management system designed to evaluate and enhance the optimization degree within manufacturing operations for improved business planning. The proposed model computes predictive data about production forecasts (times, yields, quantity of items produced) to assist operators in filling in these metrics for newly introduced items. It then assesses the discrepancy between the predicted values and the actual measured production data. This assessment aims to provide metrics for evaluating the efficiency of business planning systems, providing a quantified understanding of discrepancies for more accurate profit estimates and strategic planning. The proposed approach exploits shallow and deep machine learning models and transformer-based approaches, and it is experimentally evaluated on a real-world manufacturing dataset. One planned outcome that these metrics will enable is the provision of a tool that supports manufacturing workers by completing data that they cannot define themselves and highlighting potential discrepancies between the manually entered data and the model data, at an early stage of the manufacturing process, thus avoiding errors rather than correcting them afterwards. This approach aims to increase collaboration between humans and machines, in line with the principles of Industry 5.0
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
