检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on machine learning

作者： Youngseog Chung Ian Char Jeff Schneider Machine Learning Department Machine Learning Department and Robotics Institute Carnegie Mellon University Pittsburgh PA

Calibration of probabilistic forecasts in the regression setting has been widely studied in the single dimensional case, where the output variables are assumed to be univariate. In many problem settings, however, the output variables are multi-dimensional, and in the presence of dependence across the output dimensions, measuring calibration and performing recalibration for each dimension separately can be both misleading and detrimental. In this work, we focus on representing predictive uncertainties via samples, and propose a recalibration method which accounts for the joint distribution across output dimensions to produce calibrated samples. Based on the concept of highest density regions (HDR), we define the notion of HDR calibration, and show that our recalibration method produces samples which are HDR calibrated. We demonstrate the performance of our method and the quality of the recalibrated samples on a suite of benchmark datasets in multi-dimensional regression, a real-world dataset in modeling plasma dynamics during nuclear fusion reactions, and on a decision-making application in forecasting demand.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Classification for Low-Resource Issue Tickets with BERT

Multi-Label Classification for Low-Resource Issue Tickets wi...

引用

2024 IEEE International Conference on Cybernetics and Innovations, ICCI 2024

作者： Sungthong, Chawanee Ruangtanusak, Saksorn Songmuang, Pokpong Thammasat University Faculty Of Science And Technology Department Of Computer Science Pathum Thani Thailand Bedrock Analytics Ai And Robotics Ventures Applied Machine Learning Team Bangkok Thailand

ISBN: (纸本)9798350370096

This study focuses on the problem in the field of issue ticketing systems, where the need for human involvement in classifying work task in the ticket often results in insufficient classification. Our primary focus is on a problem associated with multi-label classification. A significant challenge in this study is the dependency of our dataset on low resources, which is different from the large datasets usually used in current multi-label text classification studies. Therefore, we propose a pre-training approach for our low-resource dataset. Our methodology applies several embedding techniques, including TF-IDF, Word2Vec, and BERT (WangchanBERTa and PhayaThaiBERT). The classification models, such as Logistic Regression, Support Vector Classifiers, Decision Trees, Neural Networks, and Deep Neural Networks, are experimented in this study to assess their performance in a low-resource environment. According to our experimental results, a combination of PhayaThaiBERT and Deep Neural Networks outperforms conventional methods. The combination yielded an F1 score of 0.769 on the test dataset. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks

arXiv

引用

arXiv 2025年

作者： Hu, Hanjiang Robey, Alexander Liu, Changliu Robotics Institute Machine Learning Department Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States Robotics Institute Carnegie Mellon University United States

Large language models (LLMs) are highly vulnerable to jailbreaking attacks, wherein adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering unsafe inputs, they fail against multi-turn jailbreaks that exploit contextual drift over multiple interactions, gradually leading LLMs away from safe behavior. To address this challenge, we propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues. Our approach models the dialogue with LLMs using state-space representations and introduces a novel neural barrier function (NBF) to detect and filter harmful queries emerging from evolving contexts proactively. Our method achieves invariant safety at each turn of dialogue by learning a safety predictor that accounts for adversarial queries, preventing potential context drift toward jailbreaks. Extensive experiments under multiple LLMs show that our NBF-based safety steering outperforms safety alignment baselines, offering stronger defenses against multi-turn jailbreaks while maintaining a better trade-off between safety and helpfulness under different multi-turn jailbreak methods. © 2025, CC BY-NC-SA.

关键词： Invariance

来源：评论

学校读者我要写书评

暂无评论

WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models

WEDGE: A multi-weather autonomous driving dataset built from...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Marathe, Aboli Ramanan, Deva Walambe, Rahee Kotecha, Ketan Carnegie Mellon University Machine Learning Department PA United States Carnegie Mellon University Robotics Institute PA United States India India

ISBN: (纸本)9798350302493

The open road poses many challenges to autonomous perception, including poor visibility from extreme weather conditions. Models trained on good-weather datasets frequently fail at detection in these out-of-distribution settings. To aid adversarial robustness in perception, we introduce WEDGE (WEather images by DALL-E GEneration): a synthetic dataset generated with a vision-language generative model via prompting. WEDGE consists of 3360 images in 16 extreme weather conditions manually annotated with 16513 bounding boxes, supporting research in the tasks of weather classification and 2D object detection. We have analyzed WEDGE from research standpoints, verifying its effectiveness for extreme-weather autonomous perception. We establish baseline performance for classification and detection with 53.87% test accuracy and 45.41 mAP. Most importantly, WEDGE can be used to fine-tune state-of-the-art detectors, improving SOTA performance on real-world weather benchmarks (such as DAWN) by 4.48 AP for well-generated classes like trucks. WEDGE has been collected under OpenAI's terms 1 of use and is released for public use under the CC BY-NC-SA 4.0 license. The repository for this work and dataset is available at https://***/WEDGE. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Int-HRL: towards intention-based hierarchical reinforcement learning

引用

Neural Computing and Applications 2024年 1-12页

作者： Penzkofer, Anna Schaefer, Simon Strohm, Florian Bâce, Mihai Leutenegger, Stefan Bulling, Andreas Institute for Visualisation and Interactive Systems University of Stuttgart Pfaffenwaldring 5A Stuttgart70569 Germany Machine Learning for Robotics Technical University of Munich Boltzmannstrasse 3 Munich85748 Germany Department of Computer Science KU Leuven box 2600 Andreas Vesaliusstraat 13 Leuven3000 Belgium

While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating information inherent to the structure of the decision problem but at the cost of having to discover or use human-annotated sub-goals that guide the learning process. We show that intentions of human players, i.e. the precursor of goal-oriented decisions, can be robustly predicted from eye gaze even for the long-horizon sparse rewards task of Montezuma’s Revenge–one of the most challenging RL tasks in the Atari2600 game suite. We propose Int-HRL: Hierarchical RL with intention-based sub-goals that are inferred from human eye gaze. Our novel sub-goal extraction pipeline is fully automatic and replaces the need for manual sub-goal annotation by human experts. Our evaluations show that replacing hand-crafted sub-goals with automatically extracted intentions leads to an HRL agent that is significantly more sample efficient than previous methods. © The Author(s) 2024.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Guided Decoding for Robot On-line Motion Generation and Adaption 23

Guided Decoding for Robot On-line Motion Generation and Adap...

引用

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Chen, Nutan Cseke, Botond Aljalbout, Elie Paraschos, Alexandros Alles, Marvin Van Der Smagt, Patrick Machine Learning Research Lab Volkswagen Group Germany Robotics and Perception Group Department of Informatics Switzerland Uzh Eth Zurich Department of Neuroinformatics Switzerland Eötvös Loránd University Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350373578

We present a novel motion generation approach for robot arms, with high degrees of freedom, in complex settings that can adapt online to obstacles or new via points. learning from Demonstration facilitates rapid adaptation to new tasks and optimizes the utilization of accumulated expertise by allowing robots to learn and generalize from demonstrated trajectories. We train a transformer architecture, based on conditional variational autoencoder, on a large dataset of simulated trajectories used as demonstrations. Our architecture learns essential motion generation skills from these demonstrations and is able to adapt them to meet auxiliary tasks. Additionally, our approach implements auto-regressive motion generation to enable real-time adaptations, as, for example, introducing or changing via-points, and velocity and acceleration constraints. Using beam search, we present a method for further adaption of our motion generator to avoid obstacles. We show that our model successfully generates motion from different initial and target points and that is capable of generating trajectories that navigate complex tasks across different robotic platforms. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review on Industry Revolution 4.0 to Predict Maintenance and Life Time of machines in Manufacturing Industry 3

Systematic Literature Review on Industry Revolution 4.0 to P...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Sowmya, P. Ravichandran, Sathish Kumar Rakshitha Department of Robotics and Artificial Intelligence Karnataka Nitte India Christ University School of Engineering and Technology Department of Computer Science Karnataka Bangalore India Department of Artificial Intelligence and Machine Learning Karnataka Nitte India

ISBN: (纸本)9781665462167

Industry 4.0 is digitized revolution for manufacturers or companies where in new technologies are imbibed into their production system for their day-to-day operations or activities. So that their overall economic needs and efficiency can be improved. In manufacturing industry maintenance of the equipment is the key concern. When the equipment requires maintenance, it has to be done at the earliest, failing which companies will have to face consequences in terms of loss of customers, time and money. Solution is provided to this problem in terms of a technique called predictive maintenance. The content of the article focuses on different predictive maintenance strategies, which help manufacturers to forecast if equipment/component will fail so that its maintenance and repair can be scheduled exactly before the component fails. The results will be useful for manufacturers to understand the importance of industry 4.0 for predictive maintenance. © 2023 IEEE.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

PID-inspired inductive biases for deep reinforcement learning in partially observable control tasks 23

PID-inspired inductive biases for deep reinforcement learnin...

引用

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

作者： Ian Char Jeff Schneider Machine Learning Department Carnegie Mellon University Pittsburgh PA Machine Learning Department Robotics Institute Carnegie Mellon University Pittsburgh PA

Deep reinforcement learning (RL) has shown immense potential for learning to control systems through data alone. However, one challenge deep RL faces is that the full state of the system is often not observable. When this is the case, the policy needs to leverage the history of observations to infer the current state. At the same time, differences between the training and testing environments makes it critical for the policy not to overfit to the sequence of observations it sees at training time. As such, there is an important balancing act between having the history encoder be flexible enough to extract relevant information, yet be robust to changes in the environment. To strike this balance, we look to the PID controller for inspiration. We assert the PID controller's success shows that only summing and differencing are needed to accumulate information over time for many control tasks. Following this principle, we propose two architectures for encoding history: one that directly uses PID features and another that extends these core ideas and can be used in arbitrary control tasks. When compared with prior approaches, our encoders produce policies that are often more robust and achieve better performance on a variety of tracking tasks. Going beyond tracking tasks, our policies achieve 1.7x better performance on average over previous state-of-the-art methods on a suite of locomotion control tasks. Code available at https://***/IanChar/GPIDE

关键词：

来源：评论

学校读者我要写书评

暂无评论

One Policy to Run Them All: an End-to-end learning Approach to Multi-Embodiment Locomotion 8

One Policy to Run Them All: an End-to-end Learning Approach ...

引用

8th Conference on Robot learning, CoRL 2024

作者： Bohlinger, Nico Czechmanowski, Grzegorz Krupka, Maciej Kicki, Piotr Walas, Krzysztof Peters, Jan Tateo, Davide Department of Computer Science Technical University of Darmstadt Germany Institute of Robotics and Machine Intelligence Poznan University of Technology Poland Research Department: Systems AI for Robot Learning Germany IDEAS NCBR Warsaw Poland Hessian.AI Germany Centre for Cognitive Science Germany

Deep Reinforcement learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world. © 2024 Proceedings of machine learning Research.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AN EXPERIMENTAL DESIGN PERSPECTIVE ON MODEL-BASED REINFORCEMENT learning 10

AN EXPERIMENTAL DESIGN PERSPECTIVE ON MODEL-BASED REINFORCEM...

引用

10th International Conference on learning Representations, ICLR 2022

作者： Mehta, Viraj Paria, Biswajit Schneider, Jeff Ermon, Stefano Neiswanger, Willie Robotics Insitute Machine Learning Department Carnegie Mellon University PittsburghPA United States Computer Science Department Stanford University StanfordCA United States

In many practical applications of RL, it is expensive to observe state transitions from the environment. For example, in the problem of plasma control for nuclear fusion, computing the next state for a given state-action pair requires querying an expensive transition function which can lead to many hours of computer simulation or dollars of scientific research. Such expensive data collection prohibits application of standard RL algorithms which usually require a large number of observations to learn. In this work, we address the problem of efficiently learning a policy while making a minimal number of state-action queries to the transition function. In particular, we leverage ideas from Bayesian optimal experimental design to guide the selection of state-action queries for efficient learning. We propose an acquisition function that quantifies how much information a state-action pair would provide about the optimal solution to a Markov decision process. At each iteration, our algorithm maximizes this acquisition function, to choose the most informative state-action pair to be queried, thus yielding a data-efficient RL approach. We experiment with a variety of simulated continuous control problems and show that our approach learns an optimal policy with up to 5-1, 000× less data than model-based RL baselines and 103 - 105× less data than model-free RL baselines. We also provide several ablated comparisons which point to substantial improvements arising from the principled method of obtaining data. © 2022 ICLR 2022 - 10th International Conference on learning Representationss. All rights reserved.

关键词： Markov processes

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：