检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Vaswani, Namrata Selim, Mohamed Y. Gibert, Renee Serrell The Electrical and Computer Engineering Department Iowa State University United States The Minority Engineering Program Purdue University United States

Signal Processing (SP) and Machine Learning (ML) rely on good math and coding knowledge, in particular, linear algebra, probability, and complex numbers. A good grasp of these relies on scalar algebra learned in middle school. The ability to understand and use scalar algebra well, in turn, relies on a good foundation in basic arithmetic. Because of various systemic barriers, many students are not able to build a strong foundation in arithmetic in elementary school. This leads them to struggle with algebra and everything after that. Since math learning is cumulative, the gap between those without a strong early foundation and everyone else keeps increasing over the school years and becomes difficult to fill in college. In this article we discuss how SP faculty and graduate students can play an important role in starting, and participating in, university-run (or other) out-of-school math support programs to supplement students’ learning. Two example programs run by the authors (CyMath at ISU and Ab7G at Purdue) are briefly described. The second goal of this article is to use our perspective as SP, and engineering, educators who have seen the long-term impact of elementary school math teaching policies, to provide some simple almost zero cost suggestions that elementary schools could adopt to improve math learning: (i) more math practice in school, (ii) send small amounts of homework (individual work is critical in math), and (iii) parent awareness (math resources, need for early math foundation, clear in-school test information and sharing of feedback from the tests). In summary, good early math support (in school and through out-of-school programs) can help make SP and ML more accessible. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models

arXiv

引用

arXiv 2024年

作者： Yi, Jihun Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of School of Computer Science and Engineering Soongsil University Seoul Korea Republic of Department of Electrical and Computer Engineering and Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

The task of image anomaly detection (IAD) aims to identify deviations from normality in image data. These anomalies are patterns that deviate significantly from what the IAD model has learned from the data during training. However, in real-world scenarios, the criteria for what constitutes normality often change, necessitating the reclassification of previously anomalous instances as normal. To address this challenge, we propose a new scenario termed "normality addition," involving the post-training adjustment of decision boundaries to incorporate new normalities. To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model. NAND performs normality detection which detect patterns related to the intended normality within images based on textual descriptions. We then modify the results of a pre-trained IAD model to implement this normality addition. Using the benchmark dataset in IAD, MVTec AD, we establish an evaluation protocol for the normality addition task and empirically demonstrate the effectiveness of the NAND method. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Optimal first-order algorithms as a function of inequalities

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2557-2625页

作者： Chanwoo Park Ernest K. Ryu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts Department of Mathematical Sciences Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plasmonic BICs as Biosensors with Better Detectivity

Plasmonic BICs as Biosensors with Better Detectivity

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Li, Zhichao Prasad, Ciril S. Wang, Xielin Naik, Gururaj V. Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States

Plasmonic sensors exhibit high sensitivity due to enhanced local fields. But, their detectivity is poor because of their poor Q-factors. Using a plasmonic BIC, we experimentally demonstrate enhanced Q-factors in a pla... 详细信息

ISBN: (纸本)9781957171258

关键词： Q factor measurement

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 12

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PER...

引用

12th International Conference on Learning Representations, ICLR 2024

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 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/. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Spirograph Method and Reconfigurable Intelligent Surface for Future Communication Systems

Joint Design of Spirograph Method and Reconfigurable Intelli...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Yafis, Balqis Huang, Jane-Hwa Yu, Chih-Min Wang, Li-Chun National Yang Ming Chiao Tung University Eecs Int'l Graduate Program Hsinchu Taiwan National Chi Nan University Dept. of Electrical Engineering Nantou County Taiwan Chung Yuan Christian University Department of Information and Computer Engineering Taoyuan City Taiwan

ISBN: (纸本)9798350351255

Reconfigurable Intelligent Surface (RIS) is a transformative technology using the passive beamforming capabilities to create the programmable wireless environments. However, the control overhead is a challenging issue. The system needs to deliver the high-precision reflection coefficients to the RIS controller, for adjusting the phase shifts of the numerous RIS elements. Therefore, we propose a Spirograph-based discrete beamdirection strategy, which selects a set of non-uniformly distributed beam directions based on the generic patterns generated by the Spirograph (SG). We evaluate the achievable data rate and the number of controlling bits of SG-based method. We compare the SG-based method, the ideal continuous phase-shift method, and the SISO method. Simulation results show that with the properly-selected discrete beam directions, the SG-based method can achieve a comparable data rate as the ideal method, while having a lower control overhead. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Optically-generated focused ultrasound for noninvasive brain stimulation with ultrahigh precision

引用

Light(Science & Applications) 2022年第11期11卷 2817-2831页

作者： Yueming Li Ying Jiang Lu Lan Xiaowei Ge Ran Cheng Yuewei Zhan Guo Chen Linli Shi Runyu Wang Nan Zheng Chen Yang Ji-Xin Cheng Department of Mechanical Engineering Boston UniversityBostonMA 02215USA Graduate Program for Neuroscience Boston UniversityBostonMA 02215USA Department of Electrical and Computer Engineering Boston UniversityBostonMA 02215USA Department of Chemistry Boston UniversitBostonMA 02215USA Department of Biomedical Engineering Boston UniversityBostonMA 02215USA Division of Materials Science and Engineering Boston UniversityBostonMA 02215USA Department of Biological Engineering Massachusetts Institute of TechnologyCambridgeMA 02142USA

High precision neuromodulation is a powerful tool to decipher neurocircuits and treat neurological *** non-invasive neuromodulation methods offer limited precision at the milimeter ***,we report opticallygenerated focused ultrasound(OFUS)for non-invasive brain stimulation with ultrahigh *** is generated by a soft optoacoustic pad(SOAP)fabricated through embedding candle soot nanoparticles in a curved polydimethylsiloxane *** generates a transcranial ultrasound focus at 15 MHz with an ultrahigh lateral resolution of 83μm,which is two orders of magnitude smaller than that of conventional transcranial-focused ultrasound(tFUS).Here,we show effective OFUS neurostimulation in vitro with a single ultrasound *** demonstrate submillimeter transcranial stimulation of the mouse motor cortex in *** acoustic energy of 0.6 mJ/cm?,four orders of magnitude less than that of tFUS,is suffcient for successful OFUS *** offers new capabilities for neuroscience studies and disease treatments by delivering a focus with ultrahigh precision noninvasively.

关键词： SOAP stimulation precision

来源：评论

学校读者我要写书评

暂无评论

ADMM-SRNet: Alternating Direction Method of Multipliers Based Sparse Representation Network for One-Class Classification

引用

IEEE Transactions on Image Processing 2023年 32卷 2843-2856页

作者： Chiou, Chien-Yu Lee, Kuang-Ting Huang, Chun-Rong Chung, Pau-Choo National Cheng Kung University Department of Electrical Engineering Tainan 701 Taiwan National Chung Hsing University Department of Computer Science and Engineering Taichung 402 Taiwan National Cheng Kung University Cross College Elite Program and Academy of Innovative Semiconductor and Sustainable Manufacturing Tainan 701 Taiwan

One-class classification aims to learn one-class models from only in-class training samples. Because of lacking out-of-class samples during training, most conventional deep learning based methods suffer from the feature collapse problem. In contrast, contrastive learning based methods can learn features from only in-class samples but are hard to be end-to-end trained with one-class models. To address the aforementioned problems, we propose alternating direction method of multipliers based sparse representation network (ADMM-SRNet). ADMM-SRNet contains the heterogeneous contrastive feature (HCF) network and the sparse dictionary (SD) network. The HCF network learns in-class heterogeneous contrastive features by using contrastive learning with heterogeneous augmentations. Then, the SD network models the distributions of the in-class training samples by using dictionaries computed based on ADMM. By coupling the HCF network, SD network and the proposed loss functions, our method can effectively learn discriminative features and one-class models of the in-class training samples in an end-to-end trainable manner. Experimental results show that the proposed method outperforms state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet-30 datasets under one-class classification settings. Code is available at https://***/nchucvml/ADMM-SRNet. © 1992-2012 IEEE.

关键词： contrastive learning deep learning dictionary learning One-class classification sparse representation

来源：评论

学校读者我要写书评

暂无评论

One-Way Quantum Repeater with Rare-Earth-Ions Doped in Solids

arXiv

引用

arXiv 2024年

作者： Lei, Yisheng Department of Electrical and Computer Engineering and Applied Physics Program Northwestern University EvanstonIL60208 United States

Quantum repeaters are proposed to overcome exponential photon loss over distance in fibers. One-way quantum repeaters eliminate the need for two-way classical communications, which can potentially outperform quantum memory based quantum repeaters. I propose that rare-earth-ions doped in solids and coupled with nano-cavity can be used to generate photonic cluster state efficiently, which serve as good platforms for one-way quantum repeater nodes. In addition, I propose a multiplexed scheme of photonic tree cluster state generation with multiple quantum emitters. With less than 100 quantum emitters, secret key rates can reach the order of MHz over a few thousand kilometers. This proposal is especially useful for generating large scale photonic cluster state, which is essential for correcting operational errors during processing in quantum repeater nodes. © 2024, CC BY.

关键词： Metal ions

来源：评论

学校读者我要写书评

暂无评论

The Deep Learning Approach For American Sign Language Detection

The Deep Learning Approach For American Sign Language Detect...

引用

2022 IEEE Creative Communication and Innovative Technology, ICCIT 2022

作者： Pangestu, Gusti Heryadi, Yaya Lukas Suparta, Wayan Arifin, Yulyani Bina Nusantara University School of Computer Science Computer Science Department Binus Graduate Program Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Faculty of Engineering Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9781665468763

Sign language has importance rule to deal with communication process especially with impairments hearing people. Sign language detection also attract lot of researchers to join the challenge of research to detect and recognize the sign language in the field of computer Science. Hence, there is still no any standard approach and method to recognize the meaning in every pose of sign language. This research proposed a mechanism to detect Alphabet American Sign Language by utilizing Convolutional Neural Network (CNN) process. The CNN approach was chosen based on the ability and capability to recognize image. In this research, MNIST dataset is used for traning and testing process. The proposed CNN architecture produced 97% of accuracy that outperform the previous research using the same dataset which made this architecture promising. © 2022 IEEE.

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：