检索结果-内蒙古大学图书馆

Design Automation Conference

作者： Chieh-Lin Tsai Chun-Feng Wu Yuan-Hao Chang Han-Wen Hu Yung-Chun Lee Hsiang-Pang Li Tei-Wei Kuo Department of Computer Science and Information Engineering National Taiwan University Department of Computer Science National Yang Ming Chiao Tung University Institute of Information Science Academia Sinica Taiwan Macronix International Co. Ltd Department of Electrical Engineering National Tsing Hua University Mohamed Bin Zayed University of Artificial Intelligence NTU High Performance and Scientific Computing Center National Taiwan University

Random forest is a popular ensemble machine-learning algorithm for classification and regression tasks. However, the irregular tree shapes and non-deterministic memory access patterns make it hard for the current von Neumann architecture to handle random forest efficiently. This paper proposes a digital 3D TCAM-based accelerator for the random forest, adopting the idea of processing-in-memory (PIM) to reduce data movement. By utilizing this accelerator, we propose a TCAM-based approach to provide real-time inference with low energy consumption, making it suitable for edge or embedded environments. In the experiments, the proposed approach achieves an average of 3.13 times higher throughput with 22 times more energy saving than the GPU approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mentored learning: improving generalization and convergence of student learner via teaching feedback

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 15891-15935页

作者： Xiaofeng Cao Yaming Guo Heng Tao Shen Ivor W. Tsang James T. Kwok School of Artificial Intelligence Jilin University Changchun China and Australian Artifcial Intelligence Institute (AAII) University of Technology Sydney (UTS) NSW Australia School of Artificial Intelligence Jilin University Changchun China School of Computer Science and Technology Tongji University Shanghai China and School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Centre for Frontier AI Research and Institute of High Performance Computing Agency for Science Technology and Research(A*STAR) Singapore Singapore and College of Computing and Data Science Nanyang Technological University Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong SAR China

Student learners typically engage in an iterative process of actively updating its hypotheses, like active learning. While this behavior can be advantageous, there is an inherent risk of introducing mistakes through incremental updates including weak initialization, inaccurate or insignificant history states, resulting in expensive convergence cost. In this work, rather than solely monitoring the update of the learner's status, we propose monitoring the disagreement w.r.t. $\mathcal{F}^\mathcal{T}(\cdot)$ between the learner and teacher, and call this new paradigm "Mentored Learning", which consists of 'how to teach' and 'how to learn'. By actively incorporating feedback that deviates from the learner's current hypotheses, convergence will be much easier to analyze without strict assumptions on learner's historical status, then deriving tighter generalization bounds on error and label complexity. Formally, we introduce an approximately optimal teaching hypothesis, hT, incorporating a tighter slack term $\left(1+\mathcal{F}^{\mathcal{T}}(\widehat{h}_t)\right)\Delta_t$ to replace the typical 2Δt used in hypothesis pruning. Theoretically, we demonstrate that, guided by this teaching hypothesis, the learner can converge to tighter generalization bounds on error and label complexity compared to non-educated learners who lack guidance from a teacher: 1) the generalization error upper bound can be reduced from R(h*)+4ΔT-1 to approximately R(hT )+2ΔT-1, and 2) the label complexity upper bound can be decreased from 4θ(TR(h*) + 2O(√T)) to approximately 2θ(2TR(hT) + 3O(√T)). To adhere strictly to our assumption, self-improvement of teaching is proposed when hT loosely approximates h*. In the context of learning, we further consider two teaching scenarios: instructing a white-box and black-box learner. Experiments validate this teaching concept and demonstrate superior generalization performance compared to fundamental active learning strategies, such as IWAL (Beygelzimer et al

关键词： machine teaching hypothesis pruning active learning error disagreement convergence generalization error label complexity

来源：评论

学校读者我要写书评

暂无评论

Parallel Bayesian Network Structure Learning for Genome-Scale Gene Networks

Parallel Bayesian Network Structure Learning for Genome-Scal...

引用

Supercomputing Conference

作者： Sanchit Misra Md. Vasimuddin Kiran Pamnany Sriram P. Chockalingam Yong Dong Min Xie Maneesha R. Aluru Srinivas Aluru Parallel Computing Lab Intel Corporation Bangalore India Dept. of Computer Science and Engineering Indian Institute of Technology Bombay Mumbai India State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China School of Biology Georgia Institute of Technology Atlanta USA School of Computational Science and Engineering Georgia Institute of Technology Atlanta USA

Learning Bayesian networks is NP-hard. Even with recent progress in heuristic and parallel algorithms, modeling capabilities still fall short of the scale of the problems encountered. In this paper, we present a massively parallel method for Bayesian network structure learning, and demonstrate its capability by constructing genome-scale gene networks of the model plant Arabidopsis thaliana from over 168.5 million gene expression values. We report strong scaling efficiency of 75% and demonstrate scaling to 1.57 million cores of the Tianhe-2 supercomputer. Our results constitute three and five orders of magnitude increase over previously published results in the scale of data analyzed and computations performed, respectively. We achieve this through algorithmic innovations, using efficient techniques to distribute work across all compute nodes, all available processors and coprocessors on each node, all available threads on each processor and coprocessor, and vectorization techniques to maximize single thread performance.

关键词： Bayes methods Hypercubes Instruction sets Genomics Bioinformatics Coprocessors Vectors

来源：评论

学校读者我要写书评

暂无评论

Tuning Dzyaloshinskii-Moriya interaction in ferrimagnetic GdCo: A first-principles approach

引用

Physical Review B 2021年第17期103卷 174414-174414页

作者： Md Golam Morshed Khoong Hong Khoo Yassine Quessab Jun-Wen Xu Robert Laskowski Prasanna V. Balachandran Andrew D. Kent Avik W. Ghosh Department of Electrical and Computer Engineering University of Virginia Charlottesville Virginia 22904 USA Institute of High Performance Computing Agency for Science Technology and Research 1 Fusionopolis Way Connexis Singapore 138632 Singapore Center for Quantum Phenomena Department of Physics New York University New York New York 10003 USA Department of Materials Science and Engineering University of Virginia Charlottesville Virginia 22904 USA Department of Mechanical and Aerospace Engineering University of Virginia Charlottesville Virginia 22904 USA Department of Physics University of Virginia Charlottesville Virginia 22904 USA

We present a systematic analysis of our ability to tune chiral Dzyaloshinskii-Moriya interaction (DMI) in compensated ferrimagnetic Pt/GdCo/Pt1−xWx trilayers by cap layer composition. Using first-principles calculations, we show that the DMI increases rapidly for only ∼10% W and saturates thereafter, in agreement with experiments. The calculated DMI shows a spread in values around the experimental mean, depending on the atomic configuration of the cap layer interface. The saturation is attributed to the vanishing of spin-orbit coupling energy at the cap layer and the simultaneous constancy at the bottom interface. Additionally, we predict the DMI in Pt/GdCo/X (X=Ta,W,Ir) and find that W in the cap layer favors a higher DMI than Ta and Ir that can be attributed to the difference in d-band overlap around the Fermi level. Our results open up exciting combinatorial possibilities for controlling the DMI in ferrimagnets towards nucleating and manipulating ultrasmall high-speed skyrmions.

关键词： Dzyaloshinskii-Moriya interaction Ferrimagnetism Magnetic multilayers First-principles calculations

来源：评论

学校读者我要写书评

暂无评论

Implementation of an RFID-based biological sample identification and tracking system

Implementation of an RFID-based biological sample identifica...

引用

IEEE International Conference on RFID-Technology and Applications (RFID-TA)

作者： Atieh Zarabzadeh Farzad Hayati R. William G. Watson Geoff Bradley Jane Grimson Centre for Health Informatics Department of Computer Science Trinity College Dublin Ireland Department of Electronic Electrical & Computer Engineering University of Birmingham UK UCD School of Medicine and Medical Science UCD Conway Institute of Biomolecular & Biomedical Research University College Dublin Ireland Trinity Centre for High Performance Computing Trinity College Dublin Ireland

Collection, processing, storage and maintenance of samples to facilitate long-term cohort studies in biobanks, requires a system to manage samples in an effective way to prevent sample mix up and loss. Sample identification and tracking system aims to reserve data on the samples at all the times, hence RFID technology is employed. This technology allows information to be stored on the tags attached to tubes containing samples. A system is proposed, designed and prototype in the Prostate Cancer Research Consortium biobank.

关键词： Radiofrequency identification Databases Zigbee Electron tubes Biology Educational institutions Memory management

来源：评论

学校读者我要写书评

暂无评论

Tackling Instance-Dependent label Noise via a Universal Probabilistic Model

arXiv

引用

arXiv 2021年

作者： Wang, Qizhou Han, Bo Liu, Tongliang Niu, Gang Yang, Jian Gong, Chen Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering The University of Sydney Australia Japan Department of Computing Hong Kong Polytechnic University Hong Kong

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning methods with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A sample identification and tracking system for biobanks

A sample identification and tracking system for biobanks

引用

Annual IEEE Symposium on computer-Based Medical Systems

作者： Atieh Zarabzadeh Farzad Hayati R. William G. Watson Geoff Bradley Jane Grimson Centre of Health Informatics Department of Computer Science Trinity College Dublin Ireland Department of Electronic Electrical & Computer Engineering University of Binningham UK UCD School of Medicine and Medical Science UCD Conway Institute of Biomolecular & Biomedical Research University College Dublin Ireland Trinity Centre of High Performance Computing Trinity College Dublin Ireland

The discovery of biomarkers and the underlying causes of diseases are enabled through the analysis of biological samples and data stored in biobanks. Biological samples and their associated data are expensive to collect and maintain, and it is important to store and manage them efficiently. During processing, samples and data go through a number of procedures and techniques, which are often in different locations and by individuals with different access permissions. It is essential to maintain the link between the samples and their associated data throughout the processes they undergo. This paper presents a novel system of tracking samples and data from collection through processing to storage and retrieval, which is based on Radio Frequency Identification (RFID) technology. This system ensures the security and reliability of sample data as well as location-independent recording and updating of sample data, as they move along the workflow.

关键词： Diseases Radiofrequency identification Educational institutions Information retrieval high performance computing User centered design Biomarkers Prostate cancer Biomedical informatics computer science

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Kernel Framework for Large-Scale Data Modeling and Classification

An Energy-Efficient Kernel Framework for Large-Scale Data Mo...

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Paul D. Yoo Jason W.P. Ng Albert Y. Zomaya Department Computer Engineering Etisalat British Telecom (BT) Innovation Centre Khalifa University of Science Technology and Research Abu Dhabi UAE Centre of Distributed and High Performance Computing School of Information Technologies (J12) University of Sydney NSW Australia

Energy-efficient computing has now become a key challenge not only for data-center operations, but also for many other energy-driven systems, with the focus on reducing of all energy-related costs, and operational expenses, as well as its corresponding and environmental impacts. Intelligent machine-learning systems are typically performance driven. For instance, most non-parametric model-free approaches are often known to require high computational cost in order to find the global optima. Designing more accurate machine-learning systems to satisfy the market needs will hence lead to a higher likelihood of energy waste due to the increased computational cost. This paper thus introduces an energy-efficient framework for large-scale data modeling and classification. It can achieve a test error comparable to or better than the state-of-the-art machine-learning models, while at the same time, maintaining a low computational cost when dealing with large-scale data. The effectiveness of the proposed approaches has been demonstrated by our experiments with two large-scale KDD datasets: Mtv-1 and Mtv-2.

关键词： Electromyography Machine learning Energy efficiency Distributed processing

来源：评论

学校读者我要写书评

暂无评论

Attention-guided progressive neural texture fusion for high dynamic range image restoration

arXiv

引用

arXiv 2021年

作者： Chen, Jie Yang, Zaifeng Chan, Tsz Nam Li, Hui Hou, Junhui Chau, Lap-Pui The Department of Computer Science Hong Kong Baptist University Hong Kong The Institute of High Performance Computing A*STAR Singapore The Imaging Algorithm Research Department Vivo Mobile Communication Co. Ltd Shenzhen China The Department of Computer Science City University of Hong Kong Hong Kong The School of Electrical & Electronic Engineering Nanyang Technological University Singapore

high Dynamic Range (HDR) imaging via multiexposure fusion is an important task for most modern imaging platforms. In spite of recent developments in both hardware and algorithm innovations, challenges remain over content association ambiguities caused by saturation, motion, and various artifacts introduced during multi-exposure fusion such as ghosting, noise, and blur. In this work, we propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model which aims to address these issues within one framework. An efficient two-stream structure is proposed which separately focuses on texture feature transfer over saturated regions and multi-exposure tonal and texture feature fusion. A neural feature transfer mechanism is proposed which establishes spatial correspondence between different exposures based on multi-scale VGG features in the masked saturated HDR domain for discriminative contextual clues over the ambiguous image areas. A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner. In addition, we introduce several novel attention mechanisms, i.e., the motion attention module detects and suppresses the content discrepancies among the reference images;the saturation attention module facilitates differentiating the misalignment caused by saturation from those caused by motion;and the scale attention module ensures texture blending consistency between different coder/decoder scales. We carry out comprehensive qualitative and quantitative evaluations and ablation studies, which validate that these novel modules work coherently under the same framework and outperform state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Canonical convolutional neural networks

arXiv

引用

arXiv 2022年

作者： Veeramacheneni, Lokesh Wolter, Moritz Klein, Reinhard Garcke, Jochen Department of Computer Science Hochschule Bonn-Rhein-Sieg Fraunhofer Center for Machine Learning SCAI Germany High Performance Computing and Analytics Lab University of Bonn Fraunhofer Center for Machine Learning SCAI Germany Department of Computer Science University of Bonn Germany Fraunhofer Center for Machine Learning SCAI Institute for Numerical Simulation University of Bonn Germany

We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode. Additionally, similarly to weight normalization, we include a global scaling parameter. We study the initialization of the canonical form by running the power method and by drawing randomly from Gaussian or uniform distributions. Our results indicate that we can replace the power method with cheaper initializations drawn from standard distributions. The canonical re-parametrization leads to competitive normalization performance on the MNIST, CIFAR10, and SVHN data sets. Moreover, the formulation simplifies network compression. Once training has converged, the canonical form allows convenient model-compression by truncating the parameter sums. © 2022, CC BY-NC-SA.

关键词： Convolutional neural networks

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：