检索结果-内蒙古大学图书馆

2021 Computing in Cardiology, CinC 2021

作者： Han, Hyeongrok Park, Seongjae Min, Seonwoo Choi, Hyun-Soo Kim, Eunji Kim, Hyunki Park, Sangha Kim, Jinkook Park, Junsang An, Junho Lee, Kwanglo Jeong, Wonsun Chon, Sangil Ha, Kwonwoo Han, Myungkyu Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of HUINNO Co. Ltd Seoul Korea Republic of LG AI Research Seoul Korea Republic of Department of Computer Science and Engineering Kangwon National University Chuncheon Korea Republic of Department of Biological Sciences Interdisciplinary Program in Bioinformatics Interdisciplinary Program in Artificial Intelligence ASRI INMC Institute of Engineering Research Seoul National University Seoul Korea Republic of

ISBN: (纸本)9781665479165

Recently, many electrocardiogram (ECG) classification algorithms using deep learning have been proposed. The characteristics of ECG vary from dataset to dataset for various reasons (i.e., hospital, race, etc.). Therefore, it is important for a model to have high generalization performance consistently over all datasets. In this paper, as part of the PhysioNet / Computing in Cardiology Challenge 2021, we present a model developed to classify cardiac abnormalities from 12 lead and reduced-lead ECGs. In particular, to upgrade our previous model for improving generalization performance, we newly adopt constant-weighted cross-entropy loss, additional features, Mixup augmentation, and squeeze/excitation block, OneCycle learning rate scheduler, which are selected via evaluation of generalization performance using leave-one-dataset-out cross-validation setting. With the present model, our DSAILSNU team has received challenge scores of 0.55, 0.58, 0.58, 0.57 and 0.57 (ranked 2nd, 1st, 1st, 2nd, 2nd out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set, respectively. The present model achieves higher generalization performance over all versions of the hidden test set than the model submitted last year. © 2021 Creative Commons.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR

arXiv

引用

arXiv 2023年

作者： Shin, Jaeuk Kim, Giho Lee, Howon Han, Joonho Yang, Insoon The Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul08826 Korea Republic of Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Seoul08826 Korea Republic of

Designing a competent meta-reinforcement learning (meta-RL) algorithm in terms of data usage remains a central challenge to be tackled for its successful real-world applications. In this paper, we propose a sample-efficient meta-RL algorithm that learns a model of the system or environment at hand in a task-directed manner. As opposed to the standard model-based approaches to meta-RL, our method exploits the value information in order to rapidly capture the decision-critical part of the environment. The key component of our method is the loss function for learning the task inference module and the system model that systematically couples the model discrepancy and the value estimate, thereby facilitating the learning of the policy and the task inference module with a significantly smaller amount of data compared to the existing meta-RL algorithms. The idea is also extended to a non-meta-RL setting, namely an online linear quadratic regulator (LQR) problem, where our method can be simplified to reveal the essence of the strategy. The proposed method is evaluated in high-dimensional robotic control and online LQR problems, empirically verifying its effectiveness in extracting information indispensable for solving the tasks from observations in a sample efficient manner. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PERSPECTIVE OF DISENTANGLED FACTORS

arXiv

引用

arXiv 2024年

作者： Lee, Jonghyun Jung, Dahuin Lee, Saehyung Park, Junsung Shin, Juhyeon Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of AIIS ASRI INMC and ISRC Seoul National University Korea Republic of

Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test dataset during online updates, causing error accumulation. To mitigate it, TTA methods have utilized the model output’s entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error. Through experimental studies, however, we observed the unreliability of entropy as a confidence metric for TTA under biased scenarios and theoretically revealed that it stems from the neglect of the influence of latent disentangled factors of data on predictions. Building upon these findings, we introduce a novel TTA method named Destroy Your Object (DeYO), which leverages a newly proposed confidence metric named Pseudo-Label Probability Difference (PLPD). PLPD quantifies the influence of the shape of an object on prediction by measuring the difference between predictions before and after applying an object-destructive transformation. DeYO consists of sample selection and sample weighting, which employ entropy and PLPD concurrently. For robust adaptation, DeYO prioritizes samples that dominantly incorporate shape information when making predictions. Our extensive experiments demonstrate the consistent superiority of DeYO over baseline methods across various scenarios, including biased and wild. Project page is publicly available at https://***/DeYO/. Copyright © 2024, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Ahn, Hongjoon Hyeon, Jinu Oh, Youngmin Hwang, Bosun Moon, Taesup Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Samsung Advanced Institute of Technology Korea Republic of ASRI INMC IPAI/AIIS Seoul National University Korea Republic of

We argue that one of the main obstacles for developing effective Continual Reinforcement Learning (CRL) algorithms is the negative transfer issue occurring when the new task to learn arrives. Through comprehensive experimental validation, we demonstrate that such issue frequently exists in CRL and cannot be effectively addressed by several recent work on mitigating plasticity loss of RL agents. To that end, we develop Reset & Distill (R&D), a simple yet highly effective method, to overcome the negative transfer problem in CRL. R&D combines a strategy of resetting the agent’s online actor and critic networks to learn a new task and an offline learning step for distilling the knowledge from the online actor and previous expert’s action probabilities. We carried out extensive experiments on long sequence of Meta-World tasks and show that our method consistently outperforms recent baselines, achieving significantly higher success rates across a range of tasks. Our findings highlight the importance of considering negative transfer in CRL and emphasize the need for robust strategies like R&D to mitigate its detrimental effects. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Knowledge Distillation for Model Interpretability

arXiv

引用

arXiv 2023年

作者： Han, Hyeongrok Kim, Siwon Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. © 2023, CC BY-NC-SA.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Fq-Uwf: Unpaired Generative Image Enhancement for Fundus Quality Ultra-Widefield Retinal Images

SSRN

引用

SSRN 2024年

作者： Lee, Kang Geon Song, Su Jeong Lee, Soochahn Kim, Bo Hee Kong, Mingui Lee, Kyoung Mu Department of Electrical and Computer Engineering ASRI Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of Department of Ophthalmology Kangbuk Samsung Hospital Sungkyunkwan University School of Medicine Seoul Korea Republic of Sungkyunkwan University Suwon Korea Republic of School of Electrical Engineering Kookmin University Seoul Korea Republic of

Background and objectives :Ultra-widefield (UWF) retinal imaging stands as a pivotal modality for detecting major eye diseases such as diabetic retinopathy or retinal detachment. However, UWF exhibits a well-documented limitation in terms of low resolution and artifacts in the macular area, thereby constraining its clinical diagnostic accuracy, particularly for macular diseases like age-related macular *** supervised super-resolution techniques aim to address this limitation by enhancing the resolution of the macular region through the utilization of meticulously paired and aligned fundus image ground truth. However, obtaining such refined paired ground truth is a formidable *** :To tackle this issue, we propose an unpaired degradation-aware super-resolution technique for enhancing UWF retinal images. Our approach leverages recent advancements in deep learning, specifically employing generative adversarial networks and attention mechanisms. Results :Notably, our method excels in enhancing and super-resolving UWF images without relying on paired clean ground *** extensive experimentation and evaluation, we demonstrate that our approach not only produces visually pleasing results, but also establishes state-of-the-art performance in enhancing and super-resolving UWF retinal *** :We anticipate that our method will contribute to improving the accuracy of clinical assessments and treatments, ultimately leading to better patient outcomes. © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Impact of High-k Materials and Tube Numbers on CNFET Gate’s Performances

Impact of High-k Materials and Tube Numbers on CNFET Gate’s...

引用

International Conference on Smart Systems and Inventive Technology (ICSSIT)

作者： Christofer Yalung Doldet Tantraviwat Sermsak Uatrongjit Wittawat Yamwong Philosophy Program in Nanoscience and Nanotechnology (International Program/Interdisciplinary) Chiang Mai University Chiang Mai Thailand Department of Electrical Engineering Faculty of Engineering Chiang Mai University Chiang Mai Thailand Thai Microelectronics Center (TMEC) National Electronics and Computer Technology Center (NECTEC) Chachoengsao Thailand

Carbon nanotube field effect transistor (CNFET) performance is primarily influenced by a variety of characteristics, such as nanotube diameter, operating voltage, pitch, the number of tubes, dielectric constant, and contact materials. In this study, the dielectric constant and the number of carbon nanotubes (CNTs) were emphasized to analyze the propagation delay and average power dissipation of basic logic gates. Zirconium dioxide (ZrO 2 ), hafnium oxide (HfO 2 ), and silicon dioxide (SiO 2 ) were used as dielectric materials. In this experiment, the Stanford CNFET model was utilized, and variable factors such as the number of CNTs and the dielectric constant $(K_{ox})$ accumulated on the nanotube gate's surface were diversified. The correlation coefficients of the delay, the average power, and the CNT numbers were also presented. Furthermore, the multi-objective genetic algorithm and the Rmethod were utilized to find the optimal K ox and the number of CNTs for minimizing the average dissipation power and the propagation delay of some logic gates designed with CNFET. For all the gates considered, the optimal number of CNTs is 4 while the dielectric constant is within the ranges of 19 to 24.

关键词： Silicon compounds Dielectric constant Correlation Logic gates CNTFETs Power dissipation Electron tubes

来源：评论

学校读者我要写书评

暂无评论

MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula

arXiv

引用

arXiv 2024年

作者： Hyeon, Sieun Jung, Kyudan Won, Jaehee Kim, Nam-Joon Ryu, Hyun Gon Lee, Hyuk-Jae Do, Jaeyoung Department of Electrical and Computer Engineering Seoul National University Korea Republic of Department of Mathematics Chung-Ang University Korea Republic of College of Liberal Studies Seoul National University Korea Republic of NVIDIA United States Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In various academic and professional settings, such as mathematics lectures or research presentations, it is often necessary to convey mathematical expressions orally. However, reading mathematical expressions aloud without accompanying visuals can significantly hinder comprehension, especially for those who are hearing-impaired or rely on subtitles due to language barriers. For instance, when a presenter reads Euler’s Formula, current Automatic Speech Recognition (ASR) models often produce a verbose and error-prone textual description (e.g., e to the power of i x equals cosine of x plus i side of x), instead of the concise LATEX format (i.e., eix = cos(x) + isin(x)), which hampers clear understanding and communication. To address this issue, we introduce MathSpeech, a novel pipeline that integrates ASR models with small Language Models (sLMs) to correct errors in mathematical expressions and accurately convert spoken expressions into structured LATEX representations. Evaluated on a new dataset derived from lecture recordings, MathSpeech demonstrates LATEX generation capabilities comparable to leading commercial Large Language Models (LLMs), while leveraging fine-tuned small language models of only 120M parameters. Specifically, in terms of CER, BLEU, and ROUGE scores for LATEX translation, MathSpeech demonstrated significantly superior capabilities compared to GPT-4o. We observed a decrease in CER from 0.390 to 0.298, and higher ROUGE/BLEU scores compared to GPT-4o. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networks

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In Shen, Xuemin Poor, H. Vincent The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

Driven by advances in generative artificial intelligence (AI) techniques and algorithms, the widespread adoption of AI-generated content (AIGC) has emerged, allowing for the generation of diverse and high-quality content. Especially, the diffusion model-based AIGC technique has been widely used to generate content in a variety of modalities. However, the real-world implementation of AIGC models, particularly on resource-constrained devices such as mobile phones, introduces significant challenges related to energy consumption and privacy concerns. To further promote the realization of ubiquitous AIGC services, we propose a novel collaborative distributed diffusion-based AIGC framework. By capitalizing on collaboration among devices in wireless networks, the proposed framework facilitates the efficient execution of AIGC tasks, optimizing edge computation resource utilization. Furthermore, we examine the practical implementation of the denoising steps on mobile phones, the impact of the proposed approach on the wireless network-aided AIGC landscape, and the future opportunities associated with its real-world integration. The contributions of this paper not only offer a promising solution to the existing limitations of AIGC services but also pave the way for future research in device collaboration, resource optimization, and the seamless delivery of AIGC services across various devices. Our code is available at https://***/HongyangDu/DistributedDiffusion. © 2023, CC BY.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Deep Subwavelength Slotted Photonic Crystals Fabricated in a Monolithic Silicon Photonics Technology

Deep Subwavelength Slotted Photonic Crystals Fabricated in a...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Arnold, Kellen P. Allen, Joshua A. Halimi, Sami I. Ryder, Landen D. Afzal, Francis O. Bian, Yusheng Aboketaf, Abdelsalam Dezfulian, Kevin Rakowski, Michal Augur, Rod Hirokawa, Takako Nummy, Karen Weiss, Sharon M. Interdisciplinary Materials Science Program Vanderbilt University 2201 WestEndAve. NashvilleTN37235 United States Department of Electrical and Computer Engineering Vanderbilt University 2201 WestEndAve. NashvilleTN37235 United States NASA GoddardSpace Flight Center Code 561 GreenbeltMD20771 United States GlobalFoundries 400 Stone Break Rd. Ext. MaltaNY12020 United States

ISBN: (纸本)9781957171258

关键词： Silicon photonics

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：