检索结果-内蒙古大学图书馆

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Jungbeom Lee Jooyoung Choi Jisoo Mok Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Department of Electrical and Computer Engineering Seoul National University and Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (纸本)9781713845393

Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object. We interpret this phenomenon using the information bottleneck principle: the final layer of a deep neural network, activated by the sigmoid or softmax activation functions, causes an information bottleneck, and as a result, only a subset of the task-relevant information is passed on to the output. We first support this argument through a simulated toy experiment and then propose a method to reduce the information bottleneck by removing the last activation function. In addition, we introduce a new pooling method that further encourages the transmission of information from non-discriminative regions to the classification. Our experimental evaluations demonstrate that this simple modification significantly improves the quality of localization maps on both the PASCAL VOC 2012 and MS COCO 2014 datasets, exhibiting a new state-of-the-art performance for weakly supervised semantic segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Annotating TSSs in Multiple Cell Types Based on DNA Sequence and RNA-seq Data via DeeReCT-TSS

引用

Genomics, Proteomics & Bioinformatics 2022年第5期20卷 959-973页

作者： Juexiao Zhou Bin Zhang Haoyang Li Longxi Zhou Zhongxiao Li Yongkang Long Wenkai Han Mengran Wang Huanhuan Cui Jingjing Li Wei Chen Xin Gao Computer Science Program ComputerElectrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia Computational Bioscience Research Center King Abdullah University of Science and TechnologyThuwal 23955-6900Saudi Arabia Department of Biology School of Life SciencesSouthern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Gene Regulation and Systems Biology School of Life SciencesSouthern University of Science and TechnologyShenzhen 518055China Academy for Advanced Interdisciplinary Studies Southern University of Science and TechnologyShenzhen 518055China

The accurate annotation of transcription start sites(TSSs)and their usage are critical for the mechanistic understanding of gene regulation in different biological *** fulfill this,specific high-throughput experimental technologies have been developed to capture TSSs in a genome-wide manner,and various computational tools have also been developed for in silico prediction of TSSs solely based on genomic *** of these computational tools cast the problem as a binary classification task on a balanced dataset,thus resulting in drastic false positive predictions when applied on the genome ***,we present Dee Re CT-TSS,a deep learningbased method that is capable of identifying TSSs across the whole genome based on both DNA sequence and conventional RNA sequencing *** show that by effectively incorporating these two sources of information,Dee Re CT-TSS significantly outperforms other solely sequence-based methods on the precise annotation of TSSs used in different cell ***,we develop a meta-learning-based extension for simultaneous TSS annotations on 10 cell types,which enables the identification of cell type-specific ***,we demonstrate the high precision of DeeReCT-TSS on two independent datasets by correlating our predicted TSSs with experimentally defined TSS chromatin *** source code for Dee Re CT-TSS is available at https://github.-com/Joshua Chou2018/Dee Re CT-TSS_release and https://***/biocode/tools/BT007316.

关键词： Transcription start site Machine learning Deep learning Meta-learning RNA sequencing

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Multi-Person Pose Detection in electrical Industrial Safety Scenarios Using YOLOv8-Pose and OpenPose

Comparative Analysis of Real-Time Multi-Person Pose Detectio...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Shang-Te Tsai Zong-Rong Wu Pin-Hsuan Lin Chin-Hsiung Chen Wei Chien Yu-Cheng Chang School of Art and Design Sanming University Fujian China Department of Technical and Vocational Program in Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Business Administration National Central University Taoyuan Taiwan Department of Electrical Engineering New Taipei Municipal Tamsui Commercial Industrial Vocational Senior High School New Taipei Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

We reviewed the application of modern technology for rapid and accurate multi-person real-time pose detection in the hazardous field of electrical engineering. We focused on two leading pose detection technologies: YOLOv8 and OpenPose. To optimize performance, we integrated these two techniques into the LSTM model for training and investigated frame rates and accuracy.

关键词： Training Accuracy Microcontrollers Neural networks Real-time systems Safety Internet of Things

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

Measuring 3D Chemistry at 1 nm Resolution with Fused Multi-Modal Electron Tomography

引用

Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of Canada 2023年第1期29卷 1394-1395页

作者： Schwartz, Jonathan Di, Zichao Wendy Jiang, Yi Cho, Min Gee Qian, Yiwen Gu, Junsi Rozeveld, Steve Ercius, Peter Fessler, Jeffrey A. Xu, Ting Scott, Mary Hovden, Robert Department of Materials Science and Engineering University of Michigan Ann Arbor MI United States Mathematics and Computer Science Division Argonne National Laboratory Lemont IL United States Advanced Photon Source Argonne National Laboratory Lemont IL United States Department of Materials Science and Engineering University of California at Berkeley Berkeley CA United States National Center for Electron Microscopy Lawrence Berkeley National Laboratory Berkeley CA United States Dow Chemical Co. Midland MI United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI United States Materials Science Division Lawrence Berkeley National Laboratory Berkeley CA United States Applied Physics Program University of Michigan Ann Arbor MI United States

来源：评论

学校读者我要写书评

暂无评论

Design and exploration of vertically stacked complementary tunneling field-effect transistors

引用

Applied Physics Express 2024年第1期17卷 014001-014001页

作者： Thoti, Narasimhulu Li, Yiming Parallel and Scientific Computing Laboratory National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Institute of Biomedical Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan

The purpose of this letter is to study the design and explore vertically stacked complementary tunneling field-effect transistors (CTFETs) using CFET technology for emerging technology nodes. As a prior work, the CTFET’s device-level simulations are implemented and deliberated in strict compliance with the experimental settings. This work comprises the study of physical and DC analyses by scaling the p- to n-CTFET separation (D pn), being a significant factor in CFET/CTFET design for its process difficulty. By utilizing the 50% benefit in footprint, the work is further extended to CTFET static random access memory implementation and characterization with hold/read noise margin analysis. © 2023 The Author(s). Published on behalf of The Japan Society of Applied Physics by IOP Publishing Ltd

关键词： Si-Ge alloys

来源：评论

学校读者我要写书评

暂无评论

NFT-Based Hydroponic Automated Control Using Adaptive Network-Based Fuzzy Inference System

NFT-Based Hydroponic Automated Control Using Adaptive Networ...

引用

Robotics, Automation and Artificial Intelligence (RAAI), IEEE International Conference on

作者： Nico Surantha Vito Vincentdo BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Department of Electrical Faculty of Scienc and EngineeringElectronics and Communication Engineering Tokyo City University Japan

The rapid population growth and industrial development in developing countries harm the agricultural sector because many agricultural lands are converted into residential or industrial areas. Applying modern agriculture technologies such as hydroponic could help to overcome the problem. However, hydroponics requires special attention in adjusting the pH and nutrient levels to maximize plant growth, so an automated system is needed to manage the process. In this research, a smart hydroponic system is proposed by applying Adaptive Networkbased Fuzzy Inference System (ANFIS) and Internet-of-Things. The IoT system consists of sensor, actuator, and data processing layer is designed to monitor and control the condition of pH and nutrition of the observed plants. Then, the ANFIS algorithm is designed to control the level of pH and nutrition. The experiment results show that the system can automatically adjust the pH and nutrient levels to the expected range for growing plants, and the fuzzy controller made using ANFIS are more accurate and stable than the fuzzy controller made using Sugeno. This study shows that ANFIS has excellent performance when controlling multiple actuators, as long as the data set has great granularity and well defined.

关键词： Fuzzy logic Training Actuators Adaptive systems Hydroponics Media Control systems

来源：评论

学校读者我要写书评

暂无评论

Quasi-Nondestructive Read Out of Ferroelectric Capacitor Polarization by Exploiting a 2TnC Cell to Relax the Endurance Requirement

TechRxiv

引用

TechRxiv 2023年

作者： Xiao, Yi Deng, Shan Zhao, Zijian Faris, Zubair Xu, Yixin Huang, Tzu-Jung Narayanan, Vijaykrishnan Ni, Kai Microsystems Engineering Ph.D. program Rochester Institute of Technology RochesterNY14623 United States Department of Computer Science and Engineering Penn State University University ParkPA16802 United States Department of Electrical and Microelectronic Engineering Rochester Institute of Technology RochesterNY14623 United States

In this work, we propose a 2TnC ferroelectric random access memory (FeRAM) cell design to realize the quasi-nondestructive readout (QNRO) of ferroelectric polarization (PFE) in a capacitor, which can relax the endurance requirement of the ferroelectric thin film and exploits the benefits of both FeRAM and ferroelectric FET (FeFET). We demonstrate that: i) QNRO sensing of PFE is conducted successfully in experiment with a ON/OFF ratio (ION/IOFF)>103, ION>10 µA, and read endurance>106 cycles, which can relax the FeRAM endurance requirement by 106x;ii) optimization of the cell performance can be realized by tuning the metal-ferroelectric-metal capacitor (MFM) capacitor to read transistor area ratio and read transistor threshold voltage (VTH);iii) the proposed cell structure is 3D-compatible, enabling integration of highly dense memory solution;iv) the proposed cell structure also enables compute-in-memory (CIM) applications of FeRAM, which has not been widely explored. With this technology, storage and memory-centric computing can be enabled. © 2023, CC BY.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

A Novel Resource Allocation in Software-Defined Networks for IoT Application

A Novel Resource Allocation in Software-Defined Networks for...

引用

International Conference on Software, Telecommunications and computer Networks (SoftCOM)

作者： Alexandre Ladeira de Sousa Ogobuchi Daniel OKey Renata Lopes Rosa Muhammad Saadi Demostenes Zegarra Rodriguez Department of Computer Science Federal University of Lavras Lavras Minas Gerais Brazil Graduate Program in Information Engineering Federal University of ABC Santo Andre Sao Paulo Brazil Department of Electrical Enginnering University of Central Punjab Punjab Pakistan Computer Science Department Federal University of Lavras Lavras Minas Gerais Brazil

The rapid proliferation of Internet of Things (IoT) devices has posed significant challenges for network resource allocation and management. In this paper, we propose a novel methodology for efficient resource allocation in Software-Defined Networks (SDNs) to meet the unique requirements of IoT applications. Our approach leverages the flexibility and programmability of SDN to dynamically allocate network resources based on the specific needs of IoT devices. Our proposal combines reinforcement learning with dynamic resource allocation, demonstrating its effectiveness in optimizing resource allocation and enhancing network performance. The results highlight the potential of our approach to addressing the resource challenges in SDN-based IoT environments. The proposed method obtains results superior to 30% of throughput in comparison to a traditional resource allocation in SDN to IoT applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EllipsoNet: Deep-learning-enabled optical ellipsometry for complex thin films

arXiv

引用

arXiv 2022年

作者： Wang, Ziyang Lin, Yuxuan Cosmi Zhang, Kunyan Wu, Wenjing Huang, Shengxi Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA94720 United States Department of Electrical Engineering The Pennsylvania State University University ParkPA16802 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States

Optical spectroscopy is indispensable for research and development in nanoscience and nanotechnology, microelectronics, energy, and advanced manufacturing. Advanced optical spectroscopy tools often require both specifically designed high-end instrumentation and intricate data analysis techniques. Beyond the common analytical tools, deep learning methods are well suited for interpreting high-dimensional and complicated spectroscopy data. They offer great opportunities to extract subtle and deep information about optical properties of materials with simpler optical setups, which would otherwise require sophisticated instrumentation. In this work, we propose a computational ellipsometry approach based on a conventional tabletop optical microscope and a deep learning model called EllipsoNet. Without any prior knowledge about the multilayer substrates, EllipsoNet can predict the complex refractive indices of thin films on top of these nontrivial substrates from experimentally measured optical reflectance spectra with high accuracies. This task was not feasible previously with traditional reflectometry or ellipsometry methods. Fundamental physical principles, such as the Kramers-Kronig relations, are spontaneously learned by the model without any further training. This approach enables in-operando optical characterization of functional materials within complex photonic structures or optoelectronic devices. © 2022, CC BY.

关键词： Refractive index

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：