检索结果-内蒙古大学图书馆

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Soleymani, Mahdi Mahdavifar, Hessam Javidi, Tara University of California San Diego Halicioglu Data Science Institute United States University of Michigan The Department of Electrical Engineering and Computer Science Ann Arbor United States University of California San Diego Halicioglu Data Science Institute The Department of Electrical and Computer Engineering United States

ISBN: (纸本)9781665475549

In this paper, we study the quantitative group testing problem, also known as the heavy hitter detection problem and the coin weighing problem, in a non-adaptive setting. In this problem, the aim is to recover k defective items from a group of n items with the smallest possible number of quantitative/additive tests, where each such test returns the number of defective items participating in the test. In the non-adaptive setting, that we study in this paper, all tests are designed at once and can be, in principle, run in parallel. We establish a novel construction method for designing non-adaptive test matrices with a nested structure inspired by the Plotkin concatenation in the coding theory literature. Our proposed algorithm identifies k defective items among the collection of n items with high probability using k(1 + o(1)) log (n/k) non-adaptive tests in the sub-linear regime of k = o(n). Furthermore, our analysis demonstrates that the probability of decoding failure approaches zero exponentially in k as k, n ? 8. Our approach outperforms existing state-of-the-art methods for designing non-adaptive test schemes with efficient decoders for the quantitative group testing problem in terms of the required number of measurements. © 2023 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

SyREC: A Symbolic-Regression-Based Ensemble Combiner 36

SyREC: A Symbolic-Regression-Based Ensemble Combiner

引用

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Fong, Kei Sen Motani, Mehul Department of Electrical and Computer Engineering Singapore College of Design and Engineering Singapore Institute of Data Science Singapore N.1 Institute for Health Singapore National University of Singapore Singapore

ISBN: (纸本)9798331527235

Symbolic Regression (SR) is the task of finding a concise white-box mathematical expression that fulfills a given machine learning (ML) objective. In this work, we introduce the first-of-its-kind SR-based ensemble combiner (SyREC) for ML which utilizes the quasi-arithmetic mean (parameterized by a function f) as an ensemble combiner and discovers f via SR. Our Sy REC demonstrates advantages over existing ensemble combiners, i.e., averaging methods and meta-learners. Compared to averaging methods, Sy REC allows for increased combiner complexity via exploring a large function class and provides a learning process to tune the ensemble combiner to the specific dataset. Compared to meta-learners, SyREC preserves important ensemble properties, like idempotency, monotonicity and boundedness, which produce predictions more consistent with the base models. We note SyREC produces a white-box ensemble combiner that lies in the intersection of both categories of existing combiners, addressing the weaknesses while capturing the strengths of each category. To evaluate Sy REC, we present experiments on 16 open-source PMLB datasets and commonly used base models, including a large variety of experiments and analyses across different settings: (i) regression and classification tasks, (ii) equally weighted combiners and custom-weighted combiners, (iii) homogeneous and heterogeneous ensembles, (iv) sequential and parallel ensembles. We find that in all these settings, SyREC shows consistent improvement over existing ensembling approaches. This indicates that SyREC is a robust ensemble combiner, which produces explainable and consistent ensemble predictions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Attention Driven Reinforcement Learning (DAD-RL) for Autonomous Decision-Making in Dynamic Environment

Deep Attention Driven Reinforcement Learning (DAD-RL) for Au...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Chowdhury, Jayabrata Shivaraman, Venkataramanan Dangi, Sumit Sundaram, Suresh Sujit, P.B. Indian Institute of Science Robert Bosch Centre for Cyber-Physical Systems Bangalore India Indian Institute of Science Department of Aerospace Engineering Bangalore India Indian Institute of Science Education and Research Department of Data Science & Engineering and Electrical Engineering & Computer Sci-ence Bhopal India

ISBN: (纸本)9781665410205

Autonomous Vehicle (AV) decision-making in ur-ban environments is inherently challenging due to the dynamic interactions with surrounding vehicles. For safe planning, AV/ego must understand the weightage of various spatiotemporal interactions in a scene. Contemporary works use colos-sal transformer architectures to encode interactions mainly for trajectory prediction, resulting in increased computational complexity. To address this issue without compromising spatiotemporal understanding and performance, we propose the simple Deep Attention Driven Reinforcement Learning (DAD-RL) framework, which dynamically assigns and incorporates the significance of surrounding vehicles into the ego's RL-driven decision-making process. We introduce an AV-centric spatiotemporal attention encoding (STAE) mechanism for learning the dynamic interactions with different surrounding vehicles. To understand map and route context, we employ a context encoder to extract features from context maps. The spatiotemporal representations combined with contextual encoding provide a comprehensive state representation. The resulting model is trained using the Soft-Actor Critic (SAC) algorithm. We evaluate the proposed framework on the SMARTS urban benchmarking scenarios without traffic signals to demonstrate that DAD-RL outperforms recent state-of-the-art methods. Furthermore, an ablation study underscores the importance of the context-encoder and spatiotemporal attention encoder in achieving superior performance. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Unified binary and multiclass margin-based classification

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 6810-6860页

作者： Yutong Wang Clayton Scott Department of Electrical Engineering and Computer Science and Michigan Institute of Data Science Department of Electrical Engineering and Computer Science and Department of Statistics University of Michigan Ann Arbor MI

The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated.

关键词： classification loss functions consistency margins label encodings

来源：评论

学校读者我要写书评

暂无评论

RETHINKING SYMBOLIC REGRESSION: MORPHOLOGY AND ADAPTABILITY FOR EVOLUTIONARY ALGORITHMS 11

RETHINKING SYMBOLIC REGRESSION: MORPHOLOGY AND ADAPTABILITY ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Fong, Kei Sen Wongso, Shelvia Motani, Mehul Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Symbolic Regression (SR) is the well-studied problem of finding closed-form analytical expressions that describe the relationship between variables in a measurement *** this paper, we rethink SR from two perspectives: morphology and ***: Current SR algorithms typically use several man-made heuristics to influence the morphology (or structure) of the expressions in the search *** man-made heuristics may introduce unintentional bias and data leakage, especially with the relatively few equation-recovery benchmark problems available for evaluating SR *** address this, we formulate a novel minimalistic approach, based on constructing a depth-aware mathematical language model trained on terminal walks of expression trees, as a replacement to these ***: Current SR algorithms tend to select expressions based on only a single fitness function (e.g., MSE on the training set).We promote the use of an adaptability framework in evolutionary SR which uses fitness functions that alternate across *** leads to robust expressions that perform well on the training set and are close to the true functional *** demonstrate this by alternating fitness functions that quantify faithfulness to values (via MSE) and empirical derivatives (via a novel theoretically justified fitness metric coined MSEDI).Proof-of-concept: We combine these ideas into a minimalistic evolutionary SR algorithm that outperforms a suite of benchmark and state of-the-art SR algorithms in problems with unknown constants added, which we claim are more reflective of SR performance for real-world *** claim is then strengthened by reproducing the superior performance on real-world regression datasets from *** researchers interested in equation-recovery problems, we also propose a set of conventions that can be used to promote fairness in comparison across SR methods and to reduce unintentional bias. © 2023 11th Internation

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints 41

Fundamental Limits of Distributed Covariance Matrix Estimati...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Rahmani, Mohammad Reza Yassaee, Mohammad Hossein Maddah-Ali, Mohammad Ali Aref, Mohammad Reza Department of Electrical Engineering Sharif University of Technology Tehran Iran Sharif Center for Information Systems and Data Science Sharif Institute for Convergence Science & Technology Tehran Iran Department of Electrical and Computer Engineering University of Minnesota Minneapolis United States

Estimating high-dimensional covariance matrices is crucial in various domains. This work considers a scenario where two collaborating agents access disjoint dimensions of m samples from a high-dimensional random vector, and they can only communicate a limited number of bits to a central server, which wants to accurately approximate the covariance matrix. We analyze the fundamental trade-off between communication cost, number of samples, and estimation accuracy. We prove a lower bound on the error achievable by any estimator, highlighting the impact of dimensions, number of samples, and communication budget. Furthermore, we present an algorithm that achieves this lower bound up to a logarithmic factor, demonstrating its near-optimality in practical settings. Copyright 2024 by the author(s)

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Culinary Quality: An Intelligent Food Grading System Employing Advanced Machine Learning Algorithms 10

Revolutionizing Culinary Quality: An Intelligent Food Gradin...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Pratap, C Benin D'Souza, Aren Amblish, Athulya Mathew, Jane Mary Srivenu, K. Babu, Leno Varghese Karunya Institute of Technology and Sciences Department of Electrical and Electronics Engineering Coimbatore India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Karunya Institute of Technology and Sciences Department of Food Processing Technology Coimbatore India

ISBN: (纸本)9798350384369

In this pioneering research, a transformative paradigm in culinary quality assessment through the implementation of an Intelligent Food Grading System (IFGS) powered by state-of-the-art machine learning algorithms is introduced. The primary objective is to revolutionize conventional food quality evaluation methods by introducing a dynamic, precise, and automated approach. The IFGS employs advanced machine learning techniques to comprehensively analyze diverse food attributes, including taste, texture, freshness, and nutritional content. This system provides a standardized and objective framework for evaluating food quality. Moreover, it caters to consumer expectations by ensuring transparency and reliability in the assessment of food products. The study delves into the intricacies of the machine learning algorithms incorporated in the IFGS, emphasizing their adaptability and continuous learning capabilities. The synergy between technological innovation and culinary expertise presented in this work encourages a broader conversation within the culinary community, inviting chefs, researchers, and enthusiasts to embrace a future where cutting-edge technology enhances and refines the culinary experience. © 2024 IEEE.

关键词： Food chemistry

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models

An Empirical Analysis on Spatial Reasoning Capabilities of L...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Shiri, Fatemeh Guo, Xiao-Yu Far, Mona Golestan Yu, Xin Haffari, Gholamreza Li, Yuan-Fang Department of Data Science & AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia School of Electrical Engineering and Computer Science University of Queensland Australia

ISBN: (纸本)9798891761643

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our new benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Pairwise Alignment Improves Graph Domain Adaptation 41

Pairwise Alignment Improves Graph Domain Adaptation

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Shikun Zou, Deyu Zhao, Han Li, Pan Department of Electrical and Computer Engineering Georgia Institute of Technology GA United States School of Data Science University of Science and Technology of China Hefei China Department of Computer Science University of Illinois Urbana-Champaign Champaign United States

Graph-based methods, pivotal for label inference over interconnected objects in many real-world applications, often encounter generalization challenges, if the graph used for model training differs significantly from the graph used for testing. This work delves into Graph Domain Adaptation (GDA) to address the unique complexities of distribution shifts over graph data, where interconnected data points experience shifts in features, labels, and in particular, connecting patterns. We propose a novel, theoretically principled method, Pairwise Alignment (Pair-Align) to counter graph structure shift by mitigating conditional structure shift (CSS) and label shift (LS). Pair-Align uses edge weights to recalibrate the influence among neighboring nodes to handle CSS and adjusts the classification loss with label weights to handle LS. Our method demonstrates superior performance in real-world applications, including node classification with region shift in social networks, and the pileup mitigation task in particle colliding experiments. For the first application, we also curate the largest dataset by far for GDA studies. Our method shows strong performance in synthetic and other existing benchmark datasets. Copyright 2024 by the author(s)

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Oppositional Harris Hawks Optimization with Deep Learning-Based Image Captioning

引用

computer Systems science & engineering 2023年第1期44卷 579-593页

作者： V.R.Kavitha K.Nimala A.Beno K.C.Ramya Seifedine Kadry Byeong-Gwon Kang Yunyoung Nam Department of Computer Science and Engineering Prathyusha Engineering CollegeThiruvallur602025India Department of Networking and Communications SRM Institute of Science and TechnologyChennaiIndia Department of Electronics and Communication Engineering Dr.Sivanthi Aditanar College of EngineeringTiruchendur628215India Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India Deparmtent of Applied Data Science Noroff University CollegeKristiansandNorway Department of Information and Communication Engineering Soonchunhyang UniversityAsanKorea Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

Image Captioning is an emergent topic of research in the domain of artificial intelligence(AI).It utilizes an integration of computer Vision(CV)and Natural Language processing(NLP)for generating the image *** use in several application areas namely recommendation in editing applications,utilization in virtual assistance,*** development of NLP and deep learning(DL)modelsfind useful to derive a bridge among the visual details and textual *** this view,this paper introduces an Oppositional Harris Hawks Optimization with Deep Learning based Image Captioning(OHHO-DLIC)*** OHHO-DLIC technique involves the design of distinct levels of ***,the feature extraction of the images is carried out by the use of EfficientNet ***,the image captioning is performed by bidirectional long short term memory(BiLSTM)model,comprising encoder as well as *** last,the oppositional Harris Hawks optimization(OHHO)based hyperparameter tuning process is performed for effectively adjusting the hyperparameter of the EfficientNet and BiLSTM *** experimental analysis of the OHHO-DLIC technique is carried out on the Flickr 8k dataset and a comprehensive comparative analysis highlighted the better performance over the recent approaches.

关键词： Image captioning natural language processing artificial intelligence machine learning deep learning

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：