检索结果-内蒙古大学图书馆

A Deep Spatiotemporal Approach in Maritime Accident Prediction: A Case Study of the Territorial Sea of South Korea

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Nourmohammadi, Zahra Nourmohammadi, Fatemeh Kim, Inhi Park, Shin Hyoung Department of Urban Systems Engineering Kongju National University Korea Republic of Department of Transportation Engineering University of Seoul Seoul02504 Korea Republic of

Predicting the risk of maritime accidents is crucial for improving traffic surveillance and marine safety. The availability of data sources and development of machine learning and deep learning methodologies have the potential to improve operational risk prediction. This study investigated the application of deep learning in both short- and long-term predictions of maritime accidents in different grid sizes by considering multiple influencing factors. Accordingly, we utilized several big data sources containing data collected from the territorial sea of South Korea, including ocean accident, vessel trajectory, ocean depth, and weather data. Seven machine learning and two deep learning algorithms were implemented and compared for three different grid sizes using daily, weekly, and monthly models. The results revealed that the proposed deep spatiotemporal ocean accident prediction (DSTOAP) model outperformed other traditional machine and deep learning algorithms in most scenarios, not all of them. For the practical application, the results of this study can guide ocean accident management and safety planners in choosing appropriate methods for different time schedules and different grid sizes according to the range of coverage of the patrol ship. © 2022, The Authors. All rights reserved.

关键词： learning algorithms

RELVIT: CONCEPT-GUIDED VISION TRANSFORMER FOR VISUAL RELATIONAL REASONING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ma, Xiaojian Nie, Weili Yu, Zhiding Jiang, Huaizu Xiao, Chaowei Zhu, Yuke Zhu, Song-Chun Anandkumar, Anima UCLA United States NVIDIA United States Northeastern University United States ASU United States UT Austin United States Caltech United States

Reasoning about visual relationships is central to how humans interpret the visual world. This task remains challenging for current deep learning algorithms since it requires addressing three key technical problems jointly: 1) identifying object entities and their properties, 2) inferring semantic relations between pairs of entities, and 3) generalizing to novel object-relation combinations, i.e. systematic generalization. In this work, we use vision transformers (ViTs) as our base model for visual reasoning and make better use of concepts defined as object entities and their relations to improve the reasoning ability of ViTs. Specifically, we introduce a novel concept-feature dictionary to allow flexible image feature retrieval at training time with concept keys. This dictionary enables two new concept-guided auxiliary tasks: 1) a global task for promoting relational reasoning, and 2) a local task for facilitating semantic object-centric correspondence learning. To examine the systematic generalization of visual reasoning models, we introduce systematic splits for the standard HICO and GQA benchmarks. We show the resulting model, Concept-guided Vision Transformer (or RelViT for short) significantly outperforms prior approaches on HICO and GQA by 16% and 13% in the original split, and by 43% and 18% in the systematic split. Our ablation analyses also reveal our model's compatibility with multiple ViT variants and robustness to hyper-parameters. Code is available. © 2022, CC BY.

关键词： learning algorithms

Multiple-criteria based active learning with fixed-size determinantal point processes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhan, Xueying Li, Qing Chan, Antoni B. Department of Computer Science City University of Hong Kong Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong

Active learning aims to achieve greater accuracy with less training data by selecting the most useful data samples from which it learns. Single-criterion based methods (i.e., informativeness and representativeness based methods) are simple and efficient;however, they lack adaptability to different real-world scenarios. In this paper, we introduce a multiple-criteria based active learning algorithm, which incorporates three complementary criteria, i.e., informativeness, representativeness and diversity, to make appropriate selections in the active learning rounds under different data types. We consider the selection process as a Determinantal Point Process, which good balance among these criteria. We refine the query selection strategy by both selecting the hardest unlabeled data sample and biasing towards the classifiers that are more suitable for the current data distribution. In addition, we also consider the dependencies and relationships between these data points in data selection by means of centroid-based clustering approaches. Through evaluations on synthetic and real-world datasets, we show that our method performs significantly better and is more stable than other multiple-criteria based AL algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jin, Xisen Lin, Bill Yuchen Rostami, Mohammad Ren, Xiang University of Southern California United States Information Sciences Institute United States

The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot learning methods), however, are mostly trained in a single shot on fixed datasets, unable to dynamically expand their knowledge;while continual learning algorithms are not specifically designed for rapid generalization. We present a new learning setup, Continual learning of Few-Shot Learners (CLIF), to address the challenges of both learning settings in a unified setup. CLIF assumes a model learns from a sequence of diverse NLP tasks arriving sequentially, accumulating knowledge for improved generalization to new tasks, while also retaining performance on the tasks learned earlier. We examine how the generalization ability is affected in the continual learning setup, evaluate a number of continual learning algorithms, and propose a novel regularized adapter generation approach. We find that catastrophic forgetting affects generalization ability to a lesser degree than performance on seen tasks;while continual learning algorithms can still bring considerable benefit to the generalization ability1 Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Effect of deep learning feature inference techniques on respiratory sounds

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Balli, Osman Kutlu, Yakup Computer Engineering Iskenderun Technical University Hatay Turkey

Analysis of respiratory sounds increases its importance every day. Many different methods are available in the analysis, and new techniques are continuing to be developed to further improve these methods. Features are extracted from audio signals and trained using different machine learning techniques. The use of deep learning, which is a different method and has increased in recent years, also shows its influence in this field. Deep learning techniques applied to the image of audio signals give good results and continue to be developed. In this study, image filters were applied to the values obtained from audio signals and the results of the features formed from this were examined in machine learning and deep learning techniques. Their results were compared with the results of methods that had previously achieved good results. © 2021, CC BY.

关键词： learning algorithms

DPTDR: Deep Prompt Tuning for Dense Passage Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tang, Zhengyang Wang, Benyou Yao, Ting Tencent China The Chinese University of Hong Kong Shenzhen China

Deep prompt tuning (DPT) has gained great success in most natural language processing (NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning (FT) still dominates. When deploying multiple retrieval tasks using the same backbone model (e.g., RoBERTa), FT-based methods are unfriendly in terms of deployment cost: each new retrieval model needs to repeatedly deploy the backbone model without reuse. To reduce the deployment cost in such a scenario, this work investigates applying DPT in dense retrieval. The challenge is that directly applying DPT in dense retrieval largely underperforms FT methods. To compensate for the performance drop, we propose two model-agnostic and task-agnostic strategies for DPT-based retrievers, namely retrieval-oriented intermediate pretraining and unified negative mining, as a general approach that could be compatible with any pre-trained language model and retrieval task. The experimental results 1 show that the proposed method (called DPTDR) outperforms previous state-of-the-art models on both MS-MARCO and Natural Questions. We also conduct ablation studies to examine the effectiveness of each strategy in DPTDR. We believe this work facilitates the industry, as it saves enormous efforts and costs of deployment and increases the utility of computing resources. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Information-theoretic Hardness of Out-of-time-order Correlators

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cotler, Jordan Schuster, Thomas Mohseni, Masoud Society of Fellows Harvard University CambridgeMA United States Black Hole Initiative Harvard University CambridgeMA United States Google Quantum AI 340 Main Street VeniceCA90291 United States Department of Physics University of California BerkeleyCA94720 United States

We establish that there are properties of quantum many-body dynamics which are efficiently learnable if we are given access to out-of-time-order correlators (OTOCs), but which require exponentially many operations in the system size if we can only measure time-ordered correlators. This implies that any experimental protocol which reconstructs OTOCs solely from time-ordered correlators must be, in certain cases, exponentially inefficient. Our proofs leverage and generalize recent techniques in quantum learning theory. Along the way, we elucidate a general definition of time-ordered versus out-of-time-order experimental measurement protocols, which can be considered as classes of adaptive quantum learning algorithms. Moreover, our results provide a theoretical foundation for novel applications of OTOCs in quantum simulations. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Doubly Fair Dynamic Pricing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Jianyu Qiao, Dan Wang, Yu-Xiang Department of Computer Science University of California Santa Barbara United States

We study the problem of online dynamic pricing with two types of fairness constraints: a procedural fairness which requires the proposed prices to be equal in expectation among different groups, and a substantive fairness which requires the accepted prices to be equal in expectation among different groups. A policy that is simultaneously procedural and substantive fair is referred to as doubly fair. We show that a doubly fair policy must be random to have higher revenue than the best trivial policy that assigns the same price to different groups. In a two-group setting, we propose an online learning algorithm for the 2-group pricing problems that achieves Õ(√T) regret, zero procedural unfairness and Õ(√T) substantive unfairness over T rounds of learning. We also prove two lower bounds showing that these results on regret and unfairness are both information-theoretically optimal up to iterated logarithmic factors. To the best of our knowledge, this is the first dynamic pricing algorithm that learns to price while satisfying two fairness constraints at the same *** Codes 91B06 (Primary) 91B24, 62P20, 62C20, 90B50 (Secondary) Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Daylight-Electrical-Thermal Coupling Model for Real-Time Zero-Energy Potential Analysis of Vacuum-Photovoltaic Glazing

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Tan, Yutong Peng, Jinqing Luo, Yimo Li, Houpei Wang, Meng Zhang, Fujia Ji, Jie Song, Aotian College of Civil Engineering Hunan University Hunan Changsha China Key Laboratory of Building Safety and Energy Efficiency of the Ministry of Education Hunan Changsha China College of Energy and Power Engineering Changsha University of Science and Technology Hunan Changsha China Hunan Red Solar New Energy Science and Technology Co. LTD Changsha China Department of Thermal Science and Energy Engineering University of Science and Technology of China Anhui Hefei China Co. LTD Guangzhou Shenzhen China

Windows are considered as the main culprit of heat loss in buildings and the development of advanced glazing is a global necessity. Vacuum integrated photovoltaic (VPV) glazing was proven to have great air conditioning energy-saving potential, while there is a lack of real-time zero-energy potential evaluation that considers the interaction between thermal, power and daylight performances. Given this context, a daylight-electrical-thermal coupling model combining machine learning algorithms was proposed for VPV glazing to evaluate its overall performance and for optimal design towards real-time zero-energy goal. All models were validated through full-scale outdoor experiments and showed acceptable errors between experimental and simulated data. Based on that, key parameters affecting the performance of the VPV glazing, namely PV coverage, emissivity of Low-E coating, pillar separation, and inner window shades were determined through sensitivity analysis. A case study of optimal design of the VPV glazing in hot summer and cold winter zone in China showed that VPV glazing with a PV coverage of 40%, a coating emissivity of 0.068, and a pillar separation of 90 mm can achieve 67% zero-energy hours throughout the year. This study can provide a validated coupled model for performance evaluation and optimization of VPV glazing for engineering applications. © 2022, The Authors. All rights reserved.

关键词： learning algorithms