检索结果-内蒙古大学图书馆

Path-Gradient Estimators for Continuous Normalizing Flows

学校读者我要写书评

暂无评论

arXiv 2022年

Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime in which the variational distribution approaches the exact target distribution. In many applications, this regime can however not be reached by a simple Gaussian variational distribution. In this work, we overcome this crucial limitation by proposing a path-gradient estimator for the considerably more expressive variational family of continuous normalizing flows. We outline an efficient algorithm to calculate this estimator and establish its superior performance empirically. © 2022, CC BY.

关键词：

learning trivializing gradient flows for lattice gauge theories

学校读者我要写书评

暂无评论

Physical Review D 2023年第5期107卷 L051504-L051504页

作者： Simone Bacchio Pan Kessel Stefan Schaefer Lorenz Vaitl Computation-based Science and Technology Research Center The Cyprus Institute Nicosia Cyprus Machine Learning Group Technische Universität Berlin Berlin Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany John von Neumann-Institut für Computing NIC Deutsches Elektronen-Synchrotron DESY Germany

We propose a unifying approach that starts from the perturbative construction of trivializing maps by Lüscher and then improves on it by learning. The resulting continuous normalizing flow model can be implemented using common tools of lattice field theory and requires several orders of magnitude fewer parameters than any existing machine learning approach. Specifically, our model can achieve competitive performance with as few as 14 parameters while existing deep-learning models have around 1 million parameters for SU(3) Yang-Mills theory on a 162 lattice. This has obvious consequences for training speed and interpretability. It also provides a plausible path for scaling machine-learning approaches toward realistic theories.

关键词： Lattice gauge theory Metropolis algorithm Monte Carlo methods

MARK MY WORDS: DANGERS OF WATERMARKED IMAGES IN IMAGENET

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bykov, Kirill Müller, Klaus-Robert Höhne, Marina M.-C. Technische Universität Berlin Machine Learning Group Berlin10587 Germany Understandable Machine Intelligence Lab ATB Potsdam14469 Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Korea University Department of Artificial Intelligence Seoul136-713 Korea Republic of Max Planck Institute for Informatics Saarbrücken66123 Germany Machine Learning Group UiT the Arctic University of Norway Tromsø9037 Norway Department of Computer Science University of Potsdam Potsdam14476 Germany

The utilization of pre-trained networks, especially those trained on ImageNet, has become a common practice in Computer Vision. However, prior research has indicated that a significant number of images in the ImageNet dataset contain watermarks, making pre-trained networks susceptible to learning artifacts such as watermark patterns within their latent spaces. In this paper, we aim to assess the extent to which popular pre-trained architectures display such behavior and to determine which classes are most affected. Additionally, we examine the impact of watermarks on the extracted features. Contrary to the popular belief that the Chinese logographic watermarks impact the "carton" class only, our analysis reveals that a variety of ImageNet classes, such as "monitor", "broom", "apron" and "safe" rely on spurious correlations. Finally, we propose a simple approach to mitigate this issue in fine-tuned networks by ignoring the encodings from the feature-extractor layer of ImageNet pre-trained networks that are most susceptible to watermark imprints. © 2023, CC BY.

关键词： Watermarking

A machine learning and Explainable AI Framework Tailored for Unbalanced Experimental Catalyst Discovery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Semnani, Parastoo Bogojeski, Mihail Bley, Florian Zhang, Zizheng Wu, Qiong Kneib, Thomas Herrmann, Jan Weisser, Christoph Patcas, Florina Müller, Klaus-Robert Machine Learning Group TU Berlin Berlin Germany Berlin Institute for the Foundations of Learning and Data Berlin Germany BASLEARN-TU Berlin BASF Joint Lab for Machine Learning TU Berlin Berlin Germany Georg-August-University Göttingen Statistics and Campus Institute Data Science Göttingen Germany BASF SE Ludwigshafen Germany Max Planck Institute for Informatics Saarbrücken Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of

The successful application of machine learning in catalyst design depends on high-quality and diverse data to ensure effective generalization to novel compositions, thereby aiding in catalyst discovery. However, due to the complex interactions of catalyst components, the design of novel catalysts has long relied on trial-and-error, a costly and labor-intensive process that results in scarce data that is heavily biased towards undesired, low-yield catalysts. Despite the increasing popularity of machine learning applications in this field, most of the efforts so far have not focused on dealing with the challenges presented by such experimental data. To address these challenges, we introduce a robust machine learning and explainable AI framework to accurately classify the catalytic yield of various compositions and identify the contributions of individual components to the yield. This framework combines a series of ML practices designed to handle the scarcity and imbalance of catalyst data. We apply the framework to the task of determining the yield of different catalyst combinations in oxidative methane coupling, and use it to evaluate the performance of a range of ML models: tree-based models (such as decision trees, random forest, and gradient boosted trees), logistic regression, support vector machines, and neural networks. These experiments demonstrate that the methods used in our framework lead to a significant improvement in the performance of all but one of the evaluated models. Additionally, the decision-making process of each ML model is analyzed by identifying the most important features for predicting catalyst performance using explainable AI (XAI) methods. Our analysis found that XAI methods, which provide class-aware explanations, such as Layer-wise Relevance Propagation, managed to identify key components that contribute specifically to high-yield catalysts. These findings align with chemical intuition and existing literature, reinforcing their validity.

关键词： Adversarial machine learning

Software for dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Anders, Christopher J. Neumann, David Samek, Wojciech Müller, Klaus-Robert Lapuschkin, Sebastian Machine Learning Group Department of Electrical Engineering and Computer Science Technische Universität Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Fraunhofer Heinrich Hertz Institute Berlin Germany Machine Learning and Communications Group Department of Electrical Engineering and Computer Science Technische Universität Berlin Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institut für Informatik Saarbrücken Germany

Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable Artificial Intelligence (XAI), approaches are available to explore the reasoning behind those complex models’ predictions. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) shows high performance. For deeper quantitative analysis, manual approaches exist, but without the right tools they are unnecessarily labor intensive. In this software paper, we introduce three software packages targeted at scientists to explore model reasoning using attribution approaches and beyond: (1) Zennit – a highly customizable and intuitive attribution framework implementing LRP and related approaches in PyTorch, (2) CoRelAy – a framework to easily and quickly construct quantitative analysis pipelines for dataset-wide analyses of explanations, and (3) ViRelAy – a web-application to interactively explore data, attributions, and analysis results. With this, we provide a standardized implementation solution for XAI, to contribute towards more reproducibility in our field. © 2021, CC BY-SA.

关键词： Deep neural networks

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Koehler, Gregor Wald, Tassilo Ulrich, Constantin Zimmerer, David Jaeger, Paul F. Franke, Jörg K.H. Kohl, Simon Isensee, Fabian Maier-Hein, Klaus H. Heidelberg Division of Medical Image Computing Germany Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Helmholtz Imaging DKFZ Germany NCT Heidelberg a partnership between DKFZ University Medical Center Heidelberg Germany Interactive Machine Learning Group DKFZ Applied Computer Vision Lab DKFZ Machine Learning Lab University of Freiburg Freiburg Germany London United Kingdom Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications. © 2023, CC BY.

关键词： Network layers

AUTRAINER: A MODULAR AND EXTENSIBLE DEEP learning TOOLKIT FOR COMPUTER AUDITION TASKS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rampp, Simon Triantafyllopoulos, Andreas Milling, Manuel Schuller, Björn W. Technical University of Munich Munich Germany GLAM - Group on Language Audio & Music Imperial College London United Kingdom MCML - Munich Center for Machine Learning Munich Germany MDSI - Munich Data Science Institute Munich Germany

This work introduces the key operating principles for autrainer, our new deep learning training framework for computer audition tasks. autrainer is a PyTorch-based toolkit that allows for rapid, reproducible, and easily extensible training on a variety of different computer audition tasks. Concretely, autrainer offers low-code training and supports a wide range of neural networks as well as preprocessing routines. In this work, we present an overview of its inner workings and key capabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

OADAT: Experimental and Synthetic Clinical Optoacoustic data for Standardized Image Processing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ozdemir, Firat Lafci, Berkan Deán-Ben, Xosé Luís Razansky, Daniel Perez-Cruz, Fernando Swiss Data Science Center ETH Zurich and EPFL Zurich Switzerland Institute of Pharmacology and Toxicology Institute for Biomedical Engineering Faculty of Medicine University of Zurich Switzerland Institute for Biomedical Engineering Department of Information Technology and Electrical Engineering ETH Zurich Switzerland Institute for Machine Learning Department of Computer Science ETH Zurich Switzerland

Optoacoustic (OA) imaging is based on excitation of biological tissues with nanosecond-duration laser pulses followed by subsequent detection of ultrasound waves generated via light-absorption-mediated thermoelastic expansion. OA imaging features a powerful combination between rich optical contrast and high resolution in deep tissues. This enabled the exploration of a number of attractive new applications both in clinical and laboratory settings. However, no standardized datasets generated with different types of experimental set-up and associated processing methods are available to facilitate advances in broader applications of OA in clinical settings. This complicates an objective comparison between new and established data processing methods, often leading to qualitative results and arbitrary interpretations of the data. In this paper, we provide both experimental and synthetic OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries. We further provide trained neural networks to tackle three important challenges related to OA image processing, namely accurate reconstruction under limited view tomographic conditions, removal of spatial undersampling artifacts and anatomical segmentation for improved image reconstruction. Specifically, we define 44 experiments corresponding to the aforementioned challenges as benchmarks to be used as a reference for the development of more advanced processing methods. © 2022, CC BY-NC-SA.

关键词： Photoacoustic effect

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zheng, Kaizhong Yu, Shujian Li, Baojuan Jenssen, Robert Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China The Department of Computer Science Vrije Universiteit Amsterdam Amsterdam and the Machine Learning Group UiT - Arctic University of Norway Tromsø Norway The Machine Learning Group UiT - Arctic University of Norway Tromsø Norway The School of Biomedical Engineering Fourth Military Medical University Xi’an China

Developing a new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus. Recently, machine learning-based classifiers using functional connectivity (FC) for psychiatric disorders and healthy controls are developed to identify brain markers. However, existing machine learning-based diagnostic models are prone to over-fitting (due to insufficient training samples) and perform poorly in new test environment. Furthermore, it is difficult to obtain explainable and reliable brain biomarkers elucidating the underlying diagnostic decisions. These issues hinder their possible clinical applications. In this work, we propose BrainIB, a new graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI), by leveraging the famed Information Bottleneck (IB) principle. BrainIB is able to identify the most informative edges in the brain (i.e., subgraph) and generalizes well to unseen data. We evaluate the performance of BrainIB against 3 baselines and 7 state-of-the-art brain network classification methods on three psychiatric datasets and observe that our BrainIB always achieves the highest diagnosis accuracy. It also discovers the subgraph biomarkers which are consistent to clinical and neuroimaging findings. The source code and implementation details of BrainIB are freely available at GitHub repository (https://***/SJYuCNEL/brain-and-Information-Bottleneck/). Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks