检索结果-内蒙古大学图书馆

Neural Approaches to SAT Solving: Design Choices and Interpretability

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Mojžíšek, David Hůla, Jan Li, Ziwei Zhou, Ziyu Janota, Mikoláš Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic University of Ostrava Ostrava Czech Republic

In this contribution, we provide a comprehensive evaluation of graph neural networks applied to Boolean satisfiability problems, accompanied by an intuitive explanation of the mechanisms enabling the model to generalize to different instances. We introduce several training improvements, particularly a novel closest assignment supervision method that dynamically adapts to the model’s current state, significantly enhancing performance on problems with larger solution spaces. Our experiments demonstrate the suitability of variable-clause graph representations with recurrent neural network updates, which achieve good accuracy on SAT assignment prediction while reducing computational demands. We extend the base graph neural network into a diffusion model that facilitates incremental sampling and can be effectively combined with classical techniques like unit propagation. Through analysis of embedding space patterns and optimization trajectories, we show how these networks implicitly perform a process very similar to continuous relaxations of MaxSAT, offering an interpretable view of their reasoning process. This understanding guides our design choices and explains the ability of recurrent architectures to scale effectively at inference time beyond their training distribution, which we demonstrate with test-time scaling experiments. Copyright © 2025, The Authors. All rights reserved.

关键词： Recurrent neural networks

Geometric Reasoning in the Embedding Space

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hůla, Jan Mojžíšek, David Janeček, Jiří Herel, David Janota, Mikoláš Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Czech Republic University of Ostrava Ostrava Czech Republic

In this contribution, we demonstrate that Graph Neural Networks and Transformers can learn to reason about geometric constraints. We train them to predict spatial position of points in a discrete 2D grid from a set of constraints that uniquely describe hidden figures containing these points. Both models are able to predict the position of points and interestingly, they form the hidden figures described by the input constraints in the embedding space during the reasoning process. Our analysis shows that both models recover the grid structure during training so that the embeddings corresponding to the points within the grid organize themselves in a 2D subspace and reflect the neighborhood structure of the grid. We also show that the Graph Neural Network we design for the task performs significantly better than the Transformer and is also easier to scale. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

Correction to “GEM: Glare or Gloom, I Can Still See You – End-to-End Multi-Modal Object Detection”

学校读者我要写书评

暂无评论

IEEE robotics and Automation Letters 2025年第6期10卷 6239-6239页

作者： Osama Mazhar Robert Babuška Jens Kober Cognitive Robotics Department Delft University of Technology Delft The Netherlands Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague Czechia

The numbering of Tables I and II in [1] was inconsistent with the text and their captions referred to the wrong datasets. The correct tables are shown in Tables I and II. Reference [19] in Table II refers to the refer... 详细信息

关键词： Object detection

From Differential to Algebraic Riccati Equations: The influence of Kalman [Historical Perspectives]

学校读者我要写书评

暂无评论

IEEE Control Systems 2017年第2期37卷 153-156页

作者： Lindquist, Anders Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Republic

Rudolf Emil Kalman is the creator of modern systems and control theory and the author of groundbreaking scientific contributions. He introduced fundamental notions, such as controllability and observability, and clarified the relationship between the state-space description of a linear system and its transfer function. He rigorously posed and completely solved the linear-quadratic optimal control problem. He developed what is now called the Kalman filter, a recursive filtering algorithm that strips unwanted noise out of a stream of data and that proved to be revolutionary. © 1991-2012 IEEE.

关键词： Linear systems

Bottleneck Identification in Resource-Constrained Project Scheduling via Constraint Relaxation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Nedbálek, Lukáš Novák, Antonín Faculty of Mathematics and Physics Charles University Prague Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic

In realistic production scenarios, Advanced Planning and Scheduling (APS) tools often require manual intervention by production planners, as the system works with incomplete information, resulting in suboptimal schedules. Often, the preferable solution is not found just because of the too-restrictive constraints specifying the optimization problem, representing bottlenecks in the schedule. To provide computer-assisted support for decision-making, we aim to automatically identify bottlenecks in the given schedule while linking them to the particular constraints to be relaxed. In this work, we address the problem of reducing the tardiness of a particular project in an obtained schedule in the resource-constrained project scheduling problem by relaxing constraints related to identified bottlenecks. We develop two methods for this purpose. The first method adapts existing approaches from the job shop literature and utilizes them for so-called untargeted relaxations. The second method identifies potential improvements in relaxed versions of the problem and proposes targeted relaxations. Surprisingly, the untargeted relaxations result in improvements comparable to the targeted relaxations. © 2025, CC BY.

关键词： Project management

Neuro-Evolutionary Approach to Physics-Aware Symbolic Regression

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kubalík, Jiří Babuška, Robert Czech Institute of Informatics Robotics and Cybernetics CTU in Prague Prague Czech Republic Dept. of Cognitive Robotics TU Delft The Netherlands CIIRC CTU in Prague Czech Republic

Symbolic regression is a technique that can automatically derive analytic models from data. Traditionally, symbolic regression has been implemented primarily through genetic programming that evolves populations of candidate solutions sampled by genetic operators, crossover and mutation. More recently, neural networks have been employed to learn the entire analytical model, i.e., its structure and coefficients, using regularized gradient-based optimization. Although this approach tunes the model’s coefficients better, it is prone to premature convergence to suboptimal model structures. Here, we propose a neuro-evolutionary symbolic regression method that combines the strengths of evolutionary-based search for optimal neural network (NN) topologies with gradient-based tuning of the network’s parameters. Due to the inherent high computational demand of evolutionary algorithms, it is not feasible to learn the parameters of every candidate NN topology to the full convergence. Thus, our method employs a memory-based strategy and population perturbations to enhance exploitation and reduce the risk of being trapped in suboptimal NNs. In this way, each NN topology can be trained using only a short sequence of backpropagation iterations. The proposed method was experimentally evaluated on three real-world test problems and has been shown to outperform other NN-based approaches regarding the quality of the models obtained. © 2025, CC BY.

关键词： Multiobjective optimization

Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS

学校读者我要写书评

暂无评论

Nature biotechnology 2025年 2025 May 23页

作者： Roman Bushuiev Anton Bushuiev Raman Samusevich Corinna Brungs Josef Sivic Tomáš Pluskal Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences Prague Czech Republic. Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic. Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Czech Republic. josef.sivic@cvut.cz. Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences Prague Czech Republic. tomas.pluskal@uochb.cas.cz.

Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we named Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas-a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.

关键词：

Review of the lumbar infusion test use in pediatric populations: state-of-the-art and future perspectives

学校读者我要写书评

暂无评论

Fluids and Barriers of the CNS 2025年第1期22卷 1-12页

作者： Novák, Vojtěch Bubeníková, Adéla Skalický, Petr Mládek, Arnošt Gerla, Václav Lalou, Afroditi Despina Vlasák, Aleš Leško, Róbert Bradáč, Ondřej Department of Neurosurgery Second Faculty of Medicine Charles University and Motol University Hospital Prague Czech Republic Department of Cognitive Systems and Neurosciences Robotics and Cybernetics Czech Institute of Informatics Czech Technical University Prague Czech Republic Department of Cardiovascular Medicine First Faculty of Medicine Charles University in Prague and General University Hospital in Prague Prague Czech Republic Department of Clinical Neurosciences Division of Neurosurgery Brain Physics Laboratory University of Cambridge & Cambridge University Hospital NHS Foundation Trust Cambridge United Kingdom Department of Neurology King’s College Hospital NHS Foundation Trust London United Kingdom Department of Radiation Sciences Faculty of Medicine Umeå University Umeå Sweden

Background: The lumbar infusion test (LIT) is a routine part of the diagnostic process of various CSF dynamics disorders in adults. However, it is rarely used in the paediatric population due to a lack of evidence substantiating its efficacy and overall indications. Methods: Articles utilizing the LIT in a paediatric cohort (≤ 18 years) were included according to the PRISMA guidelines with the Newcastle-Ottawa Scale to assess the risk of bias. This review was registered at PROSPERO database under number: CRD42024625857. Results: A total of 15 studies, yielding 441 patients, were included in the review. The most common indications for LIT were to predict shunt responsiveness in hydrocephalus and idiopathic intracranial hypertension (IIH). In IIH, the interaction between cerebrospinal fluid pressure (CSFp) and sagittal sinus pressure (SSp) may offer valuable diagnostic insights and present a novel assessment approach. The LIT is a validated tool, especially effective for predicting shunt responsiveness and detecting malfunctions in both IIH and hydrocephalus. Conclusions: Data surrounding LIT usage in children is lacking and most studies are outdated. Caution is needed when interpreting resistance to outflow (Rout) due to potential overestimation, with more attention directed to CSFp and the pressure within the venous system coupling in IIH. Future studies should focus on standardizing LIT protocols across age groups with focusing more on signal characteristics rather than individual parameters and fostering interdisciplinary collaboration to optimize diagnostic accuracy. © The Author(s) 2025.

关键词： Children Hydrocephalus Infusion testing Intracranial hypertension Lumbar infusion test Pediatric Pediatric neurosurgery

A Guide to Structureless Visual Localization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Panek, Vojtech Zhou, Qunjie Ding, Yaqing Agostinho, Sérgio Kukelova, Zuzana Sattler, Torsten Leal-Taixé, Laura in Prague Czech Republic Czech Institute of Informatics Robotics and Cybernetics CTU in Prague Czech Republic NVIDIA United States Visual Recognition Group Faculty of Electrical Engineering CTU in Prague Czech Republic

Visual localization algorithms, i.e., methods that estimate the camera pose of a query image in a known scene, are core components of many applications, including self-driving cars and augmented / mixed reality systems. State-of-the-art visual localization algorithms are structure-based, i.e., they store a 3D model of the scene and use 2D-3D correspondences between the query image and 3D points in the model for camera pose estimation. While such approaches are highly accurate, they are also rather inflexible when it comes to adjusting the underlying 3D model after changes in the scene. Structureless localization approaches represent the scene as a database of images with known poses and thus offer a much more flexible representation that can be easily updated by adding or removing images. Although there is a large amount of literature on structure-based approaches, there is significantly less work on structureless methods. Hence, this paper is dedicated to providing the, to the best of our knowledge, first comprehensive discussion and comparison of structureless methods. Extensive experiments show that approaches that use a higher degree of classical geometric reasoning generally achieve higher pose accuracy. In particular, approaches based on classical absolute or semi-generalized relative pose estimation outperform very recent methods based on pose regression by a wide margin. Compared with state-of-the-art structure-based approaches, the flexibility of structureless methods comes at the cost of (slightly) lower pose accuracy, indicating an interesting direction for future work. Copyright © 2025, The Authors. All rights reserved.

关键词： Three dimensional computer graphics