检索结果-内蒙古大学图书馆

Monitoring AI-modified content at scale: a case study on the impact of ChatGPT on AI conference peer reviews 24

学校读者我要写书评

暂无评论

Monitoring AI-modified content at scale: a case study on the...

Proceedings of the 41st International Conference on machine learning

作者： Weixin Liang Zachary Izzo Yaohui Zhang Haley Lepp Hancheng Cao Xuandong Zhao Lingjiao Chen Haotian Ye Sheng Liu Zhi Huang Daniel A. McFarland James Y. Zou Department of Computer Science Stanford University Machine Learning Department NEC Labs America Department of Electrical Engineering Stanford University Graduate School of Education Stanford University Department of Computer Science and Department of Management Science and Engineering Stanford University Department of Computer Science UC Santa Barbara Department of Biomedical Data Science Stanford University Graduate School of Education and Department of Sociology and Graduate School of Business Stanford University Department of Computer Science and Department of Electrical Engineering and Department of Biomedical Data Science Stanford University

We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.

关键词：

Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Chengmin Wang, Chao Hassan, Haseeb Shah, Himat Huang, Bingding Fränti, Pasi Machine Learning Group School of Computing University of Eastern Finland JoensuuFI-80100 Finland College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China Machine Learning Group School of Computing University of Eastern Finland JoensuuFI-80100 Finland College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China College of Blockchain industry Chengdu University of Information Technology Chengdu610225 China College of Health Science and Environmental Engineering Shenzhen Technology University Shenzhen518118 China

Bayesian inference has many advantages in robotic motion planning over four perspectives: The uncertainty quantification of the policy, safety (risk-aware) and optimum guarantees of robot’s motions, data-efficiency in reinforcement learning (RL) training, and reducing the sim2real gap when the robot is applied to real-world tasks. However, the application of Bayesian inference in robotic motion planning is lagging behind the comprehensive theory of Bayesian inference. Further, there are no comprehensive reviews to summarize the progress of Bayesian inference to give researchers a systematic understanding in robotic motion planning. This paper first provides the probabilistic theories of Bayesian inference which are the preliminary of Bayesian inference for complex cases. Second, the Bayesian estimation is given to estimate the posterior of policies or unknown functions which are used to compute the policy. Third, the classical model-based Bayesian RL and model-free Bayesian RL algorithms for robotic motion planning are summarized, while these algorithms in complex cases are also analyzed. Fourth, the analysis of Bayesian inference in inverse RL is given to infer the reward functions in a data-efficient manner. Fifth, we systematically present the hybridization of Bayesian inference and RL which is a promising direction to improve the convergence of RL for better motion planning. Sixth, given the Bayesian inference, we present the interpretable and safe robotic motion plannings which are the hot research topic recently. Finally, all algorithms reviewed in this paper are summarized analytically as the knowledge graphs, and the future of Bayesian inference for robotic motion planning is also discussed, to pave the way for data-efficient, explainable, and safe robotic motion planning strategies for practical applications. © 2023, CC BY-NC-ND.

关键词： Reinforcement learning

learning Trivializing Gradient Flows for Lattice Gauge Theories

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bacchio, Simone Kessel, Pan Schaefer, Stefan Vaitl, Lorenz 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. © 2022, CC BY.

关键词： Deep learning

XpertAI: uncovering model strategies for sub-manifolds

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Letzgus, Simon Müller, Klaus-Robert Montavon, Grégoire Machine Learning Group Technische Universität Berlin Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Berlin Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany Department of Mathematics and Computer Science Freie Universität Berlin Germany

In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g. distinguishing between ‘why is the output above 0?’ and ‘why is the output above 50?’). They should furthermore reflect the model’s behavior on the relevant data sub-manifold. In this paper, we introduce XpertAI, a framework that disentangles the prediction strategy into multiple range-specific sub-strategies and allows formulating precise queries about the model (the ‘explanandum’) as a linear combination of those sub-strategies. XpertAI is formulated generally to work alongside popular XAI attribution techniques, based on occlusion, gradient integration, or reverse propagation. Qualitative and quantitative results, demonstrate the benefits of our approach. © 2024, CC BY.

关键词： Regression analysis

S$^\text{3}$Attention: Improving Long Sequence Attention With Smoothed Skeleton Sketching

学校读者我要写书评

暂无评论

IEEE Journal of Selected Topics in Signal Processing 2024年第6期18卷 985-996页

作者： Xue Wang Tian Zhou Jianqing Zhu Jialin Liu Kun Yuan Tao Yao Wotao Yin Rong Jin HanQin Cai Alibaba Group Bellevue WA USA Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Statistics and Data Science University of Central Florida Orlando FL USA Center for Machine Learning Research Peking University Beijing China Antai College of Economics and Management Shanghai Jiao Tong University Shanghai China Meta Menlo Park CA USA Department of Statistics and Data Science and the Department of Computer Science University of Central Florida Orlando FL USA

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention structures are proposed to reduce the computation cost by inducing low rankness and approximating the whole sequence by sub-sequences. The most challenging part of those approaches is maintaining the proper balance between information preservation and computation reduction: the longer sub-sequences used, the better information is preserved, but at the price of introducing more noise and computational costs. In this paper, we propose a smoothed skeleton sketching based Attention structure, coined S $^{3}$ Attention, which significantly improves upon the previous attempts to negotiate this trade-off. S $^{3}$ Attention has two mechanisms to effectively minimize the impact of noise while keeping the linear complexity to the sequence length: a smoothing block to mix information over long sequences and a matrix sketching method that simultaneously selects columns and rows from the input matrix. We verify the effectiveness of S $^{3}$ Attention both theoretically and empirically. Extensive studies over Long Range Arena (LRA) datasets and six time-series forecasting show that S $^{3}$ Attention significantly outperforms both vanilla Attention and other state-of-the-art variants of Attention structures.

关键词： Computational modeling Complexity theory Transformers Task analysis Skeleton Kernel Noise

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum learning

学校读者我要写书评

暂无评论

arXiv 2024年

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

Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a partially contradictory body of evidence in the literature, CL finds popularity in deep learning research due to its promise of leveraging human-inspired curricula to achieve higher model performance. Yet, the subjectivity and biases that follow any necessary definition of difficulty, especially for those found in orderings derived from models or training statistics, have rarely been investigated. To shed more light on the underlying unanswered questions, we conduct an extensive study on the robustness and similarity of the most common scoring functions for sample difficulty estimation, as well as their potential benefits in CL, using the popular benchmark dataset CIFAR-10 and the acoustic scene classification task from the DCASE2020 challenge as representatives of computer vision and computer audition, respectively. We report a strong dependence of scoring functions on the training setting, including randomness, which can partly be mitigated through ensemble scoring. While we do not find a general advantage of CL over uniform sampling, we observe that the ordering in which data is presented for CL-based training plays an important role in model performance. Furthermore, we find that the robustness of scoring functions across random seeds positively correlates with CL performance. Finally, we uncover that models trained with different CL strategies complement each other by boosting predictive power through late fusion, likely due to differences in the learnt concepts. Alongside our findings, we release the aucurriculum toolkit (https://***/autrainer/aucurriculum), implementing sample difficulty and CL-based training in a modular fashion. © 2024, CC BY-NC-SA.

关键词： Contrastive learning

XPASC: Measuring Generalization in Weak Supervision by Explainability and Association

学校读者我要写书评

暂无评论

arXiv 2022年

作者： März, Luisa Asgari, Ehsaneddin Braune, Fabienne Zimmermann, Franziska Roth, Benjamin Research Group Data Mining and Machine Learning Faculty of Computer Science University of Vienna Vienna Austria Faculty of Philological and Cultural Studies University of Vienna Vienna Austria AI Innovation & Pre-Development Data:Lab Volkswagen AG Munich Germany UniVie Docotoral School Computer Science Vienna Austria CAPE Analytics Mountain ViewCA United States

Weak supervision is leveraged in a wide range of domains and tasks due to its ability to create massive amounts of labeled data, requiring only little manual effort. Standard approaches use labeling functions to specify signals that are relevant for the labeling. It has been conjectured that weakly supervised models over-rely on those signals and as a result suffer from overfitting. To verify this assumption, we introduce a novel method, XPASC (eXPlainability-Association SCore), for measuring the generalization of a model trained with a weakly supervised dataset. Considering the occurrences of features, classes and labeling functions in a dataset, XPASC takes into account the relevance of each feature for the predictions (explainability) of the model as well as the connection of the feature with the class and the labeling function (association), respectively. The explainability is measured using occlusion in this work. The association in XPASC can be measured in two variants: XPASC-CHI SQUARE measures associations relative to their statistical significance, while XPASC-PPMI measures association strength more generally. We use XPASC to analyze KNOWMAN, an adversarial architecture intended to control the degree of generalization from the labeling functions and thus to mitigate the problem of overfitting. On one hand, we show that KNOWMAN is able to control the degree of generalization through a hyperparameter. On the other hand, results and qualitative analysis show that generalization and performance do not relate one-to-one, and that the highest degree of generalization does not necessarily imply the best performance. Therefore methods that allow for controlling the amount of generalization can achieve the right degree of benign overfitting. Our contributions in this study are i) the XPASC score to measure generalization in weakly-supervised models, ii) evaluation of XPASC across datasets and models and iii) the release of the XPASC implementation. © 2022, CC BY.

关键词：

Towards Predicting Menstrual Cycle Phases Exploiting Paralinguistic Features

学校读者我要写书评

暂无评论

Towards Predicting Menstrual Cycle Phases Exploiting Paralin...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Anika A. Spiesberger Adria Mallol-Ragolta Andreas Triantafyllopoulos Björn W. Schuller CHI - Chair of Health Informatics Klinikum Rechts Der Isar Technical University of Munich Germany MCML - Munich Center for Machine Learning Germany GLAM - Group on Language Audio & Music Imperial College London UK MDSI - Munich Data Science Institute Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

As a growing number of people focus on understanding their bodies, the menstrual cycle and its impact on reproduction are gaining attention. Several studies have shown that the voice changes during the menstrual cycle. However, existing research primarily employs comparative analysis to detect these differences. This paper proposes using machine learning methods to analyse paralinguistic features extracted from women’s voices for predicting menstrual cycle phases. We leverage available data recorded during the menstrual and late follicular phases of 44 naturally cycling women. Using eight paralinguistic features, we achieve an accuracy of 60 %, showcasing the feasibility of classifying those two phases using speech signals. We discuss implications and suggest future research avenues, such as the need to use personalised approaches.

关键词： Accuracy Target tracking machine learning Feature extraction Engineering in medicine and biology

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ 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.

关键词：