检索结果-内蒙古大学图书馆

PHYSICS-INFORMED learning OF AEROSOL MICROPHYSICS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Harder, Paula Watson-Parris, Duncan Stier, Philip Strassel, Dominik Gauger, Nicolas R. Keuper, Janis Atmospheric Oceanic and Planetary Physics Department of Physics Universty of Oxford United Kingdom Fraunhofer Center High-Performance Computing Fraunhofer ITWM Germany Fraunhofer Center Machine Learning Fraunhofer Society Germany Scientific Computing TU Kaiserslautern Germany Institute for Machine Learning and Analytics

Aerosol particles play an important role in the climate system by absorbing and scattering radiation and influencing cloud properties. They are also one of the biggest sources of uncertainty for climate modeling. Many climate models do not include aerosols in sufficient detail due to computational constraints. In order to represent key processes, aerosol microphysical properties and processes have to be accounted for. This is done in the ECHAM-HAM global climate aerosol model using the M7 microphysics, but high computational costs make it very expensive to run with finer resolution or for a longer time. We aim to use machine learning to emulate the microphysics model at sufficient accuracy and reduce the computational cost by being fast at inference time. The original M7 model is used to generate data of input-output pairs to train a neural network on it. We are able to learn the variables' tendencies achieving an average R2 score of 77.1%. We further explore methods to inform and constrain the neural network with physical knowledge to reduce mass violation and enforce mass positivity. On a GPU we achieve a speed-up of up to over 64x compared to the original model. © 2022, CC BY.

关键词： Aerosols

Tensor parametric Hamiltonian operator inference

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Vijaywargiya, Arjun McQuarrie, Shane A. Gruber, Anthony Department of Applied and Computational Mathematics and Statistics University of Notre Dame United States Computational Mathematics Center for Computing Research Sandia National Laboratories Scientific Machine Learning Center for Computing Research Sandia National Laboratories

This work presents a tensor-based approach to constructing data-driven reduced-order models corresponding to semi-discrete partial differential equations with canonical Hamiltonian structure. By expressing parameter-varying operators with affine dependence as contractions of a generalized parameter vector against a constant tensor, this method leverages the operator inference framework to capture parametric dependence in the learned reduced-order model via the solution to a convex, least-squares optimization problem. This leads to a concise and straightforward implementation which compactifies previous parametric operator inference approaches and directly extends to learning parametric operators with symmetry constraints—a key feature required for constructing structure-preserving surrogates of Hamiltonian systems. The proposed approach is demonstrated on both a (non-Hamiltonian) heat equation with variable diffusion coefficient as well as a Hamiltonian wave equation with variable wave *** Codes 15A69, 35B30, 65P10 © 2025, CC BY.

关键词： Tensors

ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs 13

学校读者我要写书评

暂无评论

ProtSTonKGs: A Sophisticated Transformer Trained on Protein ...

13th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences, SWAT4HCLS 2022

作者： Balabin, Helena Hoyt, Charles Tapley Gyori, Benjamin M. Bachman, John Kodamullil, Alpha Tom Hofmann-Apitius, Martin Domingo-Fernández, Daniel Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing Sankt Augustin53757 Germany Bonn-Rhein-Sieg University of Applied Sciences Sankt Augustin53757 Germany Laboratory of Systems Pharmacology Harvard Medical School BostonMA02115 United States Fraunhofer Center for Machine Learning Germany Enveda Biosciences BoulderCO80301 United States

While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowl- edge graphs, their union can better exploit the advantages of such ap- proaches, ultimately improving representations of biology. Using mul- timodal transformers for such purposes can improve performance on context dependent classification tasks, as demonstrated by our previ- ous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce Prot- STonKGs, a transformer aimed at learning all-encompassing representa- tions of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark Prot- STonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of infor- mation, paving the foundation for future approaches that use multiple modalities for biomedical applications. Copyright © 2022 for this paper by its authors.

关键词： Natural language processing systems

Canonical convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Veeramacheneni, Lokesh Wolter, Moritz Klein, Reinhard Garcke, Jochen Department of Computer Science Hochschule Bonn-Rhein-Sieg Fraunhofer Center for Machine Learning SCAI Germany High Performance Computing and Analytics Lab University of Bonn Fraunhofer Center for Machine Learning SCAI Germany Department of Computer Science University of Bonn Germany Fraunhofer Center for Machine Learning SCAI Institute for Numerical Simulation University of Bonn Germany

We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode. Additionally, similarly to weight normalization, we include a global scaling parameter. We study the initialization of the canonical form by running the power method and by drawing randomly from Gaussian or uniform distributions. Our results indicate that we can replace the power method with cheaper initializations drawn from standard distributions. The canonical re-parametrization leads to competitive normalization performance on the MNIST, CIFAR10, and SVHN data sets. Moreover, the formulation simplifies network compression. Once training has converged, the canonical form allows convenient model-compression by truncating the parameter sums. © 2022, CC BY-NC-SA.

关键词： Convolutional neural networks

A scalable generative model for dynamical system reconstruction from neuroimaging data 38

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruct...

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Volkmann, Eric Brändle, Alena Durstewitz, Daniel Koppe, Georgia Medical Faculty Mannheim Heidelberg University Mannheim Germany Institute for Machine Learning Johannes Kepler University Linz Austria Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany Faculty of Physics and Astronomy Heidelberg University Heidelberg Germany Hector Institute for AI in Psychiatry Dept. for Psychiatry and Psychotherapy CIMH Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany

Data-driven inference of the generative dynamics underlying a set of observed time series is of growing interest in machine learning and the natural sciences. In neuroscience, such methods promise to alleviate the need to handcraft models based on biophysical principles and allow to automatize the inference of inter-individual differences in brain dynamics. Recent breakthroughs in training techniques for state space models (SSMs) specifically geared toward dynamical systems (DS) reconstruction (DSR) enable to recover the underlying system including its geometrical (attractor) and long-term statistical invariants from even short time series. These techniques are based on control-theoretic ideas, like modern variants of teacher forcing (TF), to ensure stable loss gradient propagation while training. However, as it currently stands, these techniques are not directly applicable to data modalities where current observations depend on an entire history of previous states due to a signal's filtering properties, as common in neuroscience (and physiology more generally). Prominent examples are the blood oxygenation level dependent (BOLD) signal in functional magnetic resonance imaging (fMRI) or Ca2+ imaging data. Such types of signals render the SSM's decoder model non-invertible, a requirement for previous TF-based methods. Here, exploiting the recent success of control techniques for training SSMs, we propose a novel algorithm that solves this problem and scales exceptionally well with model dimensionality and filter length. We demonstrate its efficiency in reconstructing dynamical systems, including their state space geometry and long-term temporal properties, from just short BOLD time series. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

On the influence of several factors on pathway enrichment analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mubeen, Sarah Kodamullil, Alpha Tom Hofmann-Apitius, Martin Domingo-Fernández, Daniel Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing Sankt Augustin53757 Germany University of Bonn Bonn53115 Germany Fraunhofer Center for Machine Learning Germany Enveda Biosciences BoulderCO80301 United States

Pathway enrichment analysis has become a widely used knowledge-based approach for the interpretation of biomedical data. Its popularity has led to an explosion of both enrichment methods and pathway databases. While the elegance of pathway enrichment lies in its simplicity, multiple factors can impact the results of such an analysis which may not be accounted for. Researchers may fail to give influential aspects their due, resorting instead to popular methods and gene set collections, or default settings. Despite ongoing efforts to establish set guidelines, meaningful results are still hampered by a lack of consensus or gold standards around how enrichment analysis should be conducted. Nonetheless, such concerns have prompted a series of benchmark studies specifically focused on evaluating the influence of various factors on pathway enrichment results. In this review, we organize and summarize the findings of these benchmarks to provide a comprehensive overview on the influence of these factors. Our work covers a broad spectrum of factors, spanning from methodological assumptions to those related to prior biological knowledge, such as pathway definitions and database choice. In doing so, we aim to shed light on how these aspects can lead to insignificant, uninteresting, or even contradictory results. Finally, we conclude the review by proposing future benchmarks as well as solutions to overcome some of the challenges which originate from the outlined factors. © 2022, CC BY.

关键词： Database systems

On the effects of biased quantum random numbers on the initialization of artificial neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Heese, Raoul Wolter, Moritz Mücke, Sascha Franken, Lukas Piatkowski, Nico Fraunhofer Center for Machine Learning and Fraunhofer Institute for Industrial Mathematics ITWM Germany Fraunhofer Center for Machine Learning and Fraunhofer Institute for Algorithms and Scientific Computing SCAI Germany Artificial Intelligence Group TU Dortmund University Germany Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Germany

Recent advances in practical quantum computing have led to a variety of cloud-based quantum computing platforms that allow researchers to evaluate their algorithms on noisy intermediate-scale quantum (NISQ) devices. A common property of quantum computers is that they can exhibit instances of true randomness as opposed to pseudo-randomness obtained from classical systems. Investigating the effects of such true quantum randomness in the context of machine learning is appealing, and recent results vaguely suggest that benefits can indeed be achieved from the use of quantum random numbers. To shed some more light on this topic, we empirically study the effects of hardware-biased quantum random numbers on the initialization of artificial neural network weights in numerical experiments. We find no statistically significant difference in comparison with unbiased quantum random numbers as well as biased and unbiased random numbers from a classical pseudo-random number generator. The quantum random numbers for our experiments are obtained from real quantum hardware. Copyright © 2021, The Authors. All rights reserved.

关键词： Random number generation

Predicting Properties of Oxide Glasses Using Informed Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Maier, Gregor Hamaekers, Jan Martilotti, Dominik-Sergio Ziebarth, Benedikt Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven Sankt Augustin53757 Germany Institut für Numerische Simulation Universität Bonn Friedrich-Hirzebruch-Allee 7 Bonn53115 Germany Fraunhofer Center for Machine Learning Schloss Birlinghoven Sankt Augustin53757 Germany Schott AG Hattenbergstrasse 10 Mainz55122 Germany

Many modern-day applications require the development of new materials with specific properties. In particular, the design of new glass compositions is of great industrial interest. Current machine learning methods for learning the composition-property relationship of glasses promise to save on expensive trial-and-error approaches. Even though quite large datasets on the composition of glasses and their properties already exist (i.e., with more than 350,000 samples), they cover only a very small fraction of the space of all possible glass compositions. This limits the applicability of purely data-driven models for property prediction purposes and necessitates the development of models with high extrapolation power. In this paper, we propose a neural network model which incorporates prior scientific and expert knowledge in its learning pipeline. This informed learning approach leads to an improved extrapolation power compared to blind (uninformed) neural network models. To demonstrate this, we train our models to predict three different material properties, that is, the glass transition temperature, the Young’s modulus (at room temperature), and the shear modulus of binary oxide glasses which do not contain sodium. As representatives for conventional blind neural network approaches we use five different feed-forward neural networks of varying widths and depths. For each property, we set up model ensembles of multiple trained models and show that, on average, our proposed informed model performs better in extrapolating the three properties of previously unseen sodium borate glass samples than all five conventional blind models. © 2023, CC BY-SA.

关键词： Extrapolation

Decision Support by Interpretable machine learning in Acoustic Emission Based Cutting Tool Wear Prediction

学校读者我要写书评

暂无评论

Decision Support by Interpretable Machine Learning in Acoust...

IEEE International Conference on Industrial Engineering and Engineering Management

作者： A. Schmetz C. Vahl Z. Zhen D. Reibert S. Mayer D. Zontar J. Garcke C. Brecher Fraunhofer-Institute for Production Technology IPT Aachen Germany Fraunhofer-Center for Machine Learning and Fraunhofer-Institute for Algorithms and Scientific Computing SCAI Sankt Augustin Germany Laboratory for Machine Tools and Production Engineering (WZL) RWTH Aachen University Germany

ISBN: (纸本)9781665437721

Predictive maintenance is a prominent and active field for applications of machine learning in industry in recent years. The health and wear of equipment directly influences the productivity and quality of the production process. Especially in ultra-precision manufacturing, tool wear has a major impact on the achievable quality while the wear itself cannot be measured directly in-process. In this paper we present a machine learning-based classification of the tool wear in-process using acoustic emission sensors. To increase the interpretability of the process – to open the black box model – we apply a feature importance analysis and use the obtained feature importances to provide augmented data representations to the users. These representations increase the transparency of the model's decision process and assist the users in validating the model's decisions and gain new insight into the phenomenon of tool wear itself.

关键词： Productivity Industries Engineering management machine learning Acoustic emission Industrial engineering Sensors