检索结果-南通市图书馆

Why AI still doesn't have consciousness?

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence technology 2021年第2期6卷 175-179页

作者： Deyi Li wen He Yike Guo Department of computer science and {2. Tsinghua UniversityBeijingChina Instltute of Systems Engineering Academy of Military SciencesPLABeijingChina Data science Institute Imperial College LondonUK Hongkong Baptist university Hong KongChina

Consciousness is one of the unique features of creatures,and is also the root of biological *** to now,all machines and robots havenJt had ***,will the artificial intelligence(AI)be conscious?Will robots have real intelligence without consciousness?The most primitive consciousness is the perception and expression of *** order to perceive the existence of the concept of‘Ij,a creature must first have a perceivable boundary such as skin to separate‘I’from‘non-1’.For robots,to have the self-awareness,they also need to be wrapped by a similar sensory ***,as intelligent tools,AI systems should also be regarded as the external extension of human *** tools are *** development of AI shows that intelligence can exist without *** human beings enter into the era of life intelligence from AI,it is not the AI became conscious,but that conscious lives will have strong ***,it becomes more necessary to be careful on applying AI to living creatures,even to those lower-level animals with only *** subversive revolution of such application may produce more careful thinking.

关键词： intelligence consciousness conscious

Large sequence models for sequential decision-making:a survey

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of computer science 2023年第6期17卷 25-42页

作者： Muning wen Runji LIN Hanjing WANG Yaodong yang Ying wen Luo MAI Jun WANG Haifeng ZHANG Weinan ZHANG School of Electronics Information and Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200241China Digital Brain Lab Shanghai 201306China Institute of Automation Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Institute for Artificial Intelligence Peking UniversityBeijing 100091China School of Informatics The University of EdinburghEdinburgh EH89JUUK Department of computer science University College LondonLondon WC1E 6BTUK

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision,e.g.,GPT-3 and Swin *** originally designed for prediction problems,it is natural to inquire about their suitability for sequential decision-making and reinforcement learning problems,which are typically beset by long-standing issues involving sample efficiency,credit assignment,and partial *** recent years,sequence models,especially the Transformer,have attracted increasing interest in the RL communities,spawning numerous approaches with notable effectiveness and *** survey presents a comprehensive overview of recent works aimed at solving sequential decision-making tasks with sequence models such as the Transformer,by discussing the connection between sequential decision-making and sequence modeling,and categorizing them based on the way they utilize the ***,this paper puts forth various potential avenues for future research intending to improve the effectiveness of large sequence models for sequential decision-making,encompassing theoretical foundations,network architectures,algorithms,and efficient training systems.

关键词： sequential decision-making sequence modeling the Transformer training system

LDV辅助下的全场振动测量(1):3D-DIC测量分辨率提升方法

在线全文

学校读者我要写书评

暂无评论

实验力学 2024年第4期39卷 389-398页

作者：傅愉翁洁纯郜泽仁陈冰韦宇晨缪泓于起峰深圳大学物理与光电工程学院深圳大学智能光测研究院广东深圳518060 中国科学技术大学近代力学系安徽合肥230027 国防科技大学空天科学学院湖南长沙410073

进入2.世纪之后,随着计算机处理能力的快速提升,基于高速相机的三维数字图像相关(3D-DIC)测振技术开始逐步被应用于不同的科研和工程领域。其优点是能实现全场振动测量,对测量环境的要求比较低,但在时间采样率和测量分辨率上无法满足大... 详细信息

进入2.世纪之后,随着计算机处理能力的快速提升,基于高速相机的三维数字图像相关(3D-DIC)测振技术开始逐步被应用于不同的科研和工程领域。其优点是能实现全场振动测量,对测量环境的要求比较低,但在时间采样率和测量分辨率上无法满足大部分的振动测量需求。另外一类成熟的振动测量方法是基于单像素光电探测器的激光多普勒测振技术(LDV),这类基于干涉的测量技术具有极高的时间采样率和测量分辨率,测量时对隔振要求也不高,但主要的问题是在空间域上只能实现单点或者少量稀疏点的测量。激光多普勒测振技术在应对稳态振动时,虽然可以采用扫描的方式,但受限于设备的光学景深,扫描范围非常有限,其空间采样率远不如基于图像的方法。本文提出了一种新型的振动测量方法,即利用LDV辅助3D-DIC实现全场振动测量,利用两者各自在测量分辨率和全场测量上的优势,从硬件和数据处理两个方面提升全场3D-DIC的振动测量分辨率,由特征尺寸的10^(-4)量级提升至10^(-6)~10^(-7)量级。所提方法在采用普通帧率相机和没有隔振措施的情况下仍然可以实现干涉量级的全场振动测量,满足大部分结构振动测量的需求。

关键词：振动测量数字图像相关全场测量激光多普勒测振技术

融合多注意力机制的自监督小样本医学图像分割

在线全文

学校读者我要写书评

暂无评论

计算机工程与科学 2024年第3期46卷 479-487页

作者：要媛媛刘宇航程雨菁彭梦晓郑文太原理工大学计算机科学与技术学院(大数据学院) 山西晋中030600 长治医学院山西省智能数据辅助诊疗工程研究中心山西长治046000

主流的基于全监督的深度学习分割模型在丰富的标记数据上训练时可以取得良好的效果,但医疗图像领域的图像分割存在标注成本高、分割目标种类多的问题,且往往缺少足够的标注数据。提出一个模型,通过融合自监督从数据中提取标签,利用超像... 详细信息

主流的基于全监督的深度学习分割模型在丰富的标记数据上训练时可以取得良好的效果,但医疗图像领域的图像分割存在标注成本高、分割目标种类多的问题,且往往缺少足够的标注数据。提出一个模型,通过融合自监督从数据中提取标签,利用超像素表征图像特性,进行小样本标注条件下的图像分割。引入多注意力机制使得模型更多关注图像的空间特征,位置注意模块和通道注意模块致力于单一图像内部的多尺度特征融合,而外部注意力模块显著突出了不同样本间的联系。在CHAOS健康腹部器官数据集上进行实验,1-shot极端情况下DSC达0.76,相较baseline分割结果提升3%左右。通过调整N-way-K-shot任务数来探讨小样本学习的意义,在7-shot设置下DSC有显著提升,与基于全监督的深度学习分割效果的差距在可接受范围内。

关键词：小样本注意力机制自监督原型网络

维普期刊数据库博看期刊

基于U^(2.-Net+的透水混凝土CT影像孔隙分割

在线全文

学校读者我要写书评

暂无评论

水电能源科学 2024年第2期42卷 62-66页

作者：侯斌孙水发张蕊崔文超李玉博湖北省水电工程智能视觉监测重点实验室湖北宜昌443000 三峡大学计算机与信息学院湖北宜昌443002 杭州师范大学信息科学与技术学院浙江杭州311121 湖北工业大学土木建筑与环境学院湖北武汉430000

针对现阶段主流的透水混凝土CT影像孔隙分割方法存在的问题,提出了一种堆叠高效RSU模块的U^(2.-Net+的图像分割方法。该方法通过堆叠高效的RSU模块,在网络中引入了更多的上采样节点和跳跃连接,还原了更多下采样阶段丢失的特征图细节;在... 详细信息

针对现阶段主流的透水混凝土CT影像孔隙分割方法存在的问题,提出了一种堆叠高效RSU模块的U^(2.-Net+的图像分割方法。该方法通过堆叠高效的RSU模块,在网络中引入了更多的上采样节点和跳跃连接,还原了更多下采样阶段丢失的特征图细节;在编码阶段增加了一个可学习的下采样操作,进一步提升了网络对细节的捕获能力;简化了原网络的深度监督,避免了底层特征图对融合输出特征图的负面影响;将单一的标准二分类交叉熵损失函数改为Focal loss和IoU loss组成的混合损失函数,提升了网络对高噪声孔隙的关注度;最后由于数据集的特点加网络改进的提升,原网络中各模块的中间通道数得以进一步缩减,减小了网络体积。试验结果表明,U^(2.-Net+相比U^(2.-Net†在保证轻量化和快速性的同时,平均交并比、精确度、F1得分由94.12.、88.89%、93.2.%分别提升至94.2.%、91.15%、94.2.%;U^(2.-Net+综合指标优于U-Net、U-Net++、U-Net3+、U^(2.-Net、U^(2.-Net†,各指标相较于主流的阈值分割算法至少提高2..2.%,实现了透水混凝土CT影像孔隙的精准、快速分割。

关键词：透水混凝土CT影像图像分割深度学习 U^(2.-Net

Intelligent Temperature Control System Design Based on Single-Chip Microcomputer

在线全文

学校读者我要写书评

暂无评论

Journal of Harbin Institute of technology(New Series) 2014年第3期21卷 91-94页

作者： Jun Li Xian-Lin Meng wen-Long Song college of Mechanical and Electrical Engineering Northeast Forestry University School of Municipal and Environmental Engineering Harbin Institute of Technology

A design method of an intelligent temperature control system based on single-chip microcomputer is presented in this paper. The intelligent temperature control system is divided into four parts: monitor,heater,controlled process and feedback loop. Among them,the temperature detection circuit is designed with the conductivity of water by sensor detection. The optical coupler MOC3041 is used to implement the power control circuit,whose control object is 1 kW electric heater with the 2.0 V alternating current power; keyboard and display circuit SMC1602. include four buttons and LCD display to achieve human-computer interaction; Based on single-chip system STC89C52.the sensor signal and keyboard set target temperature are compared to the power automatically in order to finish the water temperature control. Through the static and dynamic data testing,the results show that the proposed method provides an effective way to realize the real-time acquisition and control of temperature.

关键词： microcontroller temperature sensors power control SCR

外源镉胁迫下葡萄根际土壤真菌群落结构及多样性特征

在线全文

学校读者我要写书评

暂无评论

中外葡萄与葡萄酒 2024年第4期 70-76页

作者：陈海生陈韬略罗文蔡林生方昉李振宇浙江同济科技职业学院浙江杭州311231 浙江农林大学数学与计算机学院浙江杭州311300

研究镉(Cd)污染对浙江省中部山区河谷冲积土葡萄园土壤真菌群落结构和多样性的影响,探求有利于Cd污染农田土壤修复的耐Cd真菌菌群。采用Illumina Miseq高通量测序技术,分析外源Cd0、3.5、60 mg·kg^(-1)处理对葡萄根际土壤真菌群落结构... 详细信息

研究镉(Cd)污染对浙江省中部山区河谷冲积土葡萄园土壤真菌群落结构和多样性的影响,探求有利于Cd污染农田土壤修复的耐Cd真菌菌群。采用Illumina Miseq高通量测序技术,分析外源Cd0、3.5、60 mg·kg^(-1)处理对葡萄根际土壤真菌群落结构和多样性指数的影响。结果表明,各Cd处理组土壤真菌隶属于11门、30纲、60目、100科、163属,Cd污染会造成葡萄根际土壤真菌多样性和群落结构发生变化。Cd浓度为3.5 mg·kg^(-1)时会导致其Chaol指数和Shannon指数上升,而Cd浓度为60 mg·kg^(-1)时会导致上述两指数大幅度下降;土壤子囊菌门和担子菌门相对丰度在Cd浓度为3.5 mg·kg^(-1)时下降,在Cd浓度为60 mg·kg^(-1)时升高;土壤接合菌门相对丰度在Cd浓度为3.5 mg·kg^(-1)时升高,在Cd浓度为60 mg·kg^(-1)时下降。在Cd浓度为60 mg·kg^(-1)条件下存在大量的未分类的子囊菌、链格孢属、亚隔孢壳属菌群,这些菌属被认为是在河谷冲积土葡萄园土壤中高抗Cd污染的真菌菌群。研究结果可为葡萄园Cd污染土壤采用微生物修复提供依据。

关键词：镉污染真菌群落结构高通量测序葡萄

Joint optimization scheduling for water conservancy projects incomplex river networks

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Water science and Engineering 2017年第1期10卷 43-52页

作者： Qin Liu Guo-hua Fang Hong-bin Sun Xue-wen Wu college of Water Conservancy and Hydropower Engineering Hohai UniversityNanjing 210098China Canal Irrigation Management in Jiangsu Province Huaian 223000China college of computer and Information Engineering Hohai UniversityNanjing 210098China

In this study, we simulated water flow in a water conservancy project consisting of various hydraulic structures, such as sluices, pumping stations, hydropower stations, ship locks, and culverts, and developed a multi-period and multi-variable joint optimization scheduling model for flood control, drainage, and irrigation. In this model, the number of sluice holes, pump units, and hydropower station units to be opened were used as decision variables, and different optimization objectives and constraints were considered. This model was solved with improved genetic algorithms and verified using the Huaian Water Conservancy Project as an example. The results show that the use of the joint optimization scheduling led to a 10% increase in the power generation capacity and a 15% reduction in the total energy consumption. The change in the water level was reduced by 0.2. m upstream of the Yundong Sluice, and by 50% downstream of pumping stations No. 1, No. 2. and No. 4. It is clear that the joint optimization scheduling proposed in this study can effectively improve power generation capacity of the project, minimize operating costs and energy consumption, and enable more stable operation of various hydraulic structures. The results may provide references for the management of water conservancy projects in complex river networks.

关键词： Complex river network Water conservancy project Hydraulic structure Flow capacity simulation Scheduling model Optimal scheduling

在线全文

学校读者我要写书评

暂无评论

基于邻域关系感知图神经网络的DDI预测

计算机工程与科学 2024年第5期46卷 907-915页

作者：雷志超蒋嘉俊马驰卓周文静王楚正中南林业科技大学计算机与数学学院湖南长沙410004

研究药物的相互作用DDI有助于临床用药与新药研发。现有的研究技术没有充分考虑药物知识图谱中药物实体与其他药物、靶标和基因等实体的拓扑结构,以及实体之间不同关系的语义重要性。针对这些问题,提出基于邻域关系感知的图神经网络模型... 详细信息

研究药物的相互作用DDI有助于临床用药与新药研发。现有的研究技术没有充分考虑药物知识图谱中药物实体与其他药物、靶标和基因等实体的拓扑结构,以及实体之间不同关系的语义重要性。针对这些问题,提出基于邻域关系感知的图神经网络模型NRAGNN预测药物的相互作用。首先,使用图注意力学习不同关系边的权重与特征表示,强化药物实体的语义特征;然后,生成药物实体周围不同层的邻域表示,捕获药物实体的拓扑结构特征;最后,将2.药物特征表示向量进行逐元素相乘得到药物相互作用分数。实验预测结果表明,提出的NRAGNN模型在KEGG药物数据集上的ACC、AUPR、AUC-ROC和F1指标分别达到了0.8994,0.9444,0.9567和0.902.,优于当前的其他模型。

关键词：药物相互作用知识图谱邻域关系感知图注意力网络语义特征

维普期刊数据库博看期刊