检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Richard Gao Michael Deistler Jakob H. Macke Machine Learning in Science Excellence Cluster Machine Learning University of Tübingen and Tübingen AI Center Machine Learning in Science Excellence Cluster Machine Learning University of Tübingen and Tübingen AI Center and Department Empirical Inference Max Planck Institute for Intelligent Systems Tübingen Germany

Simulation-based inference (SBI) enables amortized Bayesian inference for simulators with implicit likelihoods. But when we are primarily interested in the quality of predictive simulations, or when the model cannot exactly reproduce the observed data (i.e., is misspecified), targeting the Bayesian posterior may be overly restrictive. Generalized Bayesian Inference (GBI) aims to robustify inference for (misspecified) simulator models, replacing the likelihood-function with a cost function that evaluates the goodness of parameters relative to data. However, GBI methods generally require running multiple simulations to estimate the cost function at each parameter value during inference, making the approach computationally infeasible for even moderately complex simulators. Here, we propose amortized cost estimation (ACE) for GBI to address this challenge: We train a neural network to approximate the cost function, which we define as the expected distance between simulations produced by a parameter and observed data. The trained network can then be used with MCMC to infer GBI posteriors for any observation without running additional simulations. We show that, on several benchmark tasks, ACE accurately predicts cost and provides predictive simulations that are closer to synthetic observations than other SBI methods, especially for misspecified simulators. Finally, we apply ACE to infer parameters of the Hodgkin-Huxley model given real intracellular recordings from the Allen Cell Types Database. ACE identifies better data-matching parameters while being an order of magnitude more simulation-efficient than a standard SBI method. In summary, ACE combines the strengths of SBI methods and GBI to perform robust and simulation-amortized inference for scientific simulators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simultaneous identification of models and parameters of scientific simulators 24

Simultaneous identification of models and parameters of scie...

引用

Proceedings of the 41st International Conference on machine learning

作者： Cornelius Schröder Jakob H. Macke Machine Learning in Science University of Tübingen and Tübingen AI Center Germany Machine Learning in Science University of Tübingen and Tübingen AI Center Germany and Max Planck Institute for Intelligent Systems Department Empirical Inference Tübingen Germany

Many scientific models are composed of multiple discrete components, and scientists often make heuristic decisions about which components to include. Bayesian inference provides a mathematical framework for systematically selecting model components, but defining prior distributions over model components and developing associated inference schemes has been challenging. We approach this problem in a simulation-based inference framework: We define model priors over candidate components and, from model simulations, train neural networks to infer joint probability distributions over both model components and associated parameters. Our method, simulation-based model inference (SBMI), represents distributions over model components as a conditional mixture of multivariate binary distributions in the Grassmann formalism. SBMI can be applied to any compositional stochastic simulator without requiring likelihood evaluations. We evaluate SBMI on a simple time series model and on two scientific models from neuroscience, and show that it can discover multiple data-consistent model configurations, and that it reveals nonidentifiable model components and parameters. SBMI provides a powerful tool for data-driven scientific inquiry which will allow scientists to identify essential model components and make uncertainty-informed modelling decisions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LiDAR-Based Registration Against Georeferenced Models for Globally Consistent Allocentric Maps

LiDAR-Based Registration Against Georeferenced Models for Gl...

引用

IEEE International Workshop on Safety, Security, and Rescue Robotics (SSRR)

作者： Jan Quenzel Linus T. Mallwitz Benedikt T. Arnold Sven Behnke Autonomous Intelligent Systems Group Computer Science Institute VI - Intelligent Systems and Robotics Center for Robotics and Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany Fraunhofer FIT Germany Fraunhofer IAIS Germany

ISBN: (数字)9798331510954

ISBN: (纸本)9798331510961

Modern unmanned aerial vehicles (UAVs) are irreplaceable in search and rescue (SAR) missions to obtain a situational overview or provide closeups without endangering personnel. However, UAVs heavily rely on global navigation satellite system (GNSS) for localization which works well in open spaces, but the precision drastically degrades in the vicinity of buildings. These inaccuracies hinder aggregation of diverse data from multiple sources in a unified georeferenced frame for SAR operators. In contrast, CityGML models provide approximate building shapes with accurate georeferenced poses. Besides, LiDAR works best in the vicinity of 3D structures. Hence, we refine coarse GNSS measurements by registering LiDAR maps against CityGML and digital elevation map (DEM) models as a prior for allocentric mapping. An intuitive plausibility score selects the best hypothesis based on occupancy using a 2D height map. Afterwards, we integrate the registration results in a continuous-time spline-based pose graph optimizer with LiDAR odometry and further sensing modalities to obtain globally consistent, georeferenced trajectories and maps. We evaluate the viability of our approach on multiple flights captured at two distinct testing sites. Our method successfully reduced GNSS offset errors from up-to 16 m to below 0.5 m on multiple flights. Furthermore, we obtain globally consistent maps w.r.t. prior 3D geospatial models.

关键词： Global navigation satellite system Solid modeling Laser radar Three-dimensional displays Buildings Data models Trajectory Geospatial analysis Splines (mathematics) Testing

来源：评论

学校读者我要写书评

暂无评论

Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation

arXiv

引用

arXiv 2024年

作者： Vetter, Julius Moss, Guy Schröder, Cornelius Gao, Richard Macke, Jakob H. Machine Learning in Science Excellence Cluster Machine Learning University of Tübingen Tübingen Germany Tübingen AI Center Tübingen Germany Department Empirical Inference Max Planck Institute for Intelligent Systems Tübingen Germany

Scientific modeling applications often require estimating a distribution of parameters consistent with a dataset of observations—an inference task also known as source distribution estimation. This problem can be ill-posed, however, since many different source distributions might produce the same distribution of data-consistent simulations. To make a principled choice among many equally valid sources, we propose an approach which targets the maximum entropy distribution, i.e., prioritizes retaining as much uncertainty as possible. Our method is purely sample-based—leveraging the Sliced-Wasserstein distance to measure the discrepancy between the dataset and simulations—and thus suitable for simulators with intractable likelihoods. We benchmark our method on several tasks, and show that it can recover source distributions with substantially higher entropy than recent source estimation methods, without sacrificing the fidelity of the simulations. Finally, to demonstrate the utility of our approach, we infer source distributions for parameters of the Hodgkin-Huxley model from experimental datasets with hundreds of single-neuron measurements. In summary, we propose a principled method for inferring source distributions of scientific simulator parameters while retaining as much uncertainty as possible. © 2024, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Adaptive deep probabilistic regression for real-time motor excitability state prediction from human EEG

引用

Brain Stimulation 2025年第1期18卷 400-401页

作者： Haxel, Lisa Kapoor, Jaivardhan Ahola, Oskari Kahilakoski, Olli-Pekka Kirchhoff, Miriam Roine, Timo Ziemann, Ulf Macke, Jakob H. Machine Learning in Science Excellence Cluster Machine Learning & Tübingen AI Center Germany Hertie Institute for Clinical Brain Research Department Neurology and Stroke Germany Department of Neuroscience and Biomedical Engineering Aalto University School of Science Finland Department Empirical Inference Max Planck Institute for Intelligent Systems Germany

来源：评论

学校读者我要写书评

暂无评论

Latent diffusion for neural spiking data 24

Latent diffusion for neural spiking data

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Jaivardhan Kapoor Auguste Schulz Julius Vetter Felix Pei Richard Gao Jakob H. Macke Machine Learning in Science University of Tübingen & Tübingen AI Center Tübingen Germany Machine Learning in Science University of Tübingen & Tübingen AI Center Tübingen Germany and Department Empirical Inference Max Planck Institute for Intelligent Systems Tübingen Germany

ISBN: (纸本)9798331314385

Modern datasets in neuroscience enable unprecedented inquiries into the relationship between complex behaviors and the activity of many simultaneously recorded neurons. While latent variable models can successfully extract low-dimensional embeddings from such recordings, using them to generate realistic spiking data, especially in a behavior-dependent manner, still poses a challenge. Here, we present Latent Diffusion for Neural Spiking data (LDNS), a diffusion-based generative model with a low-dimensional latent space: LDNS employs an autoencoder with structured state-space (S4) layers to project discrete high-dimensional spiking data into continuous time-aligned latents. On these inferred latents, we train expressive (conditional) diffusion models, enabling us to sample neural activity with realistic single-neuron and population spiking statistics. We validate LDNS on synthetic data, accurately recovering latent structure, firing rates, and spiking statistics. Next, we demonstrate its flexibility by generating variable-length data that mimics human cortical activity during attempted speech. We show how to equip LDNS with an expressive observation model that accounts for single-neuron dynamics not mediated by the latent state, further increasing the realism of generated samples. Finally, conditional LDNS trained on motor cortical activity during diverse reaching behaviors can generate realistic spiking data given reach direction or unseen reach trajectories. In summary, LDNS simultaneously enables inference of low-dimensional latents and realistic conditional generation of neural spiking datasets, opening up further possibilities for simulating experimentally testable hypotheses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multiview Top-k Pooling with Deep-Q-Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2985-2996页

作者： Li, Zhi-Peng Su, Hai-Long Wu, Yong- Zhang, Qin-Hu Yuan, Chang-An Gribova, Valeriya Filaretov, Vladimir Fedorovich Huang, De-Shuang Eastern Institute of Technology Zhejiang Ningbo315201 China University of Science and Technology of China School of Life Sciences Anhui Hefei230026 China Tongji University Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Shanghai201804 China Guangxi Academy of Sciences Institute of Big Data and Intelligent Computing Research Center Nanning530007 China Far Eastern Branch of the Russian Academy of Sciences Institute of Automation and Control Processes Vladivostok690041 Russia

Graph neural networks (GNNs) are extensions of deep neural networks to graph-structured data. It has already attracted widespread attention for various tasks such as node classification and link prediction. Existing research focuses more on graph convolutional neural networks (GCNs). However, it is usually overlooked that graph pooling can obtain graph representations by summarizing and down-sampling node information. Meanwhile, existing graph pooling methods mainly use top-k for node selection, but most of them consider only single view information when scoring nodes, and the k values in top-k are usually selected empirically. This work proposes the hierarchical multiview top-k pooling (HMTPool) with deep-Q-networks, which scores nodes taking into account multiview information (considering graph structure and features) and does not rely on the empirical adaptive selection of the best k value. HMTPool is a two-stage process. It first uses a variant GCN and multilayer perceptron to score the nodes from structural and feature perspectives, respectively and then performs fusion operations on the multiview information scores of the nodes. In addition, to select the optimal pooling ratio of top-k, we propose a deep-Q-network-based top-k (DTop-k) node selection method, which can adaptively select the best pooling ratio without prior knowledge. Experimental results on six TUDatasets and two Benchmarking GNNs datasets demonstrate the effectiveness of our proposed approach. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

LiDAR-based Registration against Georeferenced Models for Globally Consistent Allocentric Maps

arXiv

引用

arXiv 2024年

作者： Quenzel, Jan Mallwitz, Linus T. Arnold, Benedikt T. Behnke, Sven Autonomous Intelligent Systems Group Computer Science Institute VI – Intelligent Systems and Robotics Germany Center for Robotics Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany Fraunhofer FIT Germany Fraunhofer IAIS Germany

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping

Learning Embeddings with Centroid Triplet Loss for Object Id...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Anas Gouda Max Schwarz Christopher Reining Sven Behnke Alice Kirchheim TU Dortmund Lamarr Institute for Machine Learning and Artificial Intelligence Autonomous Intelligent Systems - Computer Science VI & Center for Robotics University of Bonn Germany Fraunhofer IML

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Foundation models are a strong trend in deep learning and computer vision. These models serve as a base for applications as they require minor or no further fine-tuning by developers to integrate into their applications. Foundation models for zero-shot object segmentation such as Segment Anything (SAM) output segmentation masks from images without any further object information. When they are followed in a pipeline by an object identification model, they can perform object detection without training. Here, we focus on training such an object identification model. A crucial practical aspect for an object identification model is to be flexible in input size (number of input images). As object identification is an image retrieval problem, a suitable method should handle multi-query multigallery situations without constraining the number of input images (e.g. by having fixed-size aggregation layers). The key solution to train such a model is the centroid triplet loss (CTL), which aggregates image features to their centroids. CTL yields high accuracy, avoids misleading training signals and keeps the model input size flexible. In our experiments, we establish a new state of the art on the ArmBench object identification task, which shows general applicability of our model. We furthermore demonstrate an integrated unseen object detection pipeline on the challenging HOPE dataset, which requires finegrained detection. There, our pipeline matches and surpasses related methods which have been trained on dataset-specific data. Code and pretrained models are available. 5

关键词： Training Location awareness Image segmentation Accuracy Pipelines Object detection Object segmentation Market research Object recognition Proposals

来源：评论

学校读者我要写书评

暂无评论

Vectorized conditional neural fields: a framework for solving time-dependent parametric partial differential equations 24

Vectorized conditional neural fields: a framework for solvin...

引用

Proceedings of the 41st International Conference on machine learning

作者： Jan Hagnberger Marimuthu Kalimuthu Daniel Musekamp Mathias Niepert Machine Learning and Simulation Lab Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany Machine Learning and Simulation Lab Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany and Stuttgart Center for Simulation Science (SimTech) and International Max Planck Research School for Intelligent Systems (IMPRS-IS) Machine Learning and Simulation Lab Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany and International Max Planck Research School for Intelligent Systems (IMPRS-IS)

Transformer models are increasingly used for solving Partial Differential Equations (PDEs). Several adaptations have been proposed, all of which suffer from the typical problems of Transformers, such as quadratic memory and time complexity. Furthermore, all prevalent architectures for PDE solving lack at least one of several desirable properties of an ideal surrogate model, such as (i) generalization to PDE parameters not seen during training, (ii) spatial and temporal zero-shot super-resolution, (iii) continuous temporal extrapolation, (iv) support for 1D, 2D, and 3D PDEs, and (v) efficient inference for longer temporal rollouts. To address these limitations, we propose Vectorized Conditional Neural Fields (VCNeFs), which represent the solution of time-dependent PDEs as neural fields. Contrary to prior methods, however, VCNeFs compute, for a set of multiple spatio-temporal query points, their solutions in parallel and model their dependencies through attention mechanisms. Moreover, VCNeF can condition the neural field on both the initial conditions and the parameters of the PDEs. An extensive set of experiments demonstrates that VCNeFs are competitive with and often outperform existing ML-based surrogate models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：