The idea of writing this book arose from the need to investigate the main principles of modern power electronic control strategies, using fuzzy logic and neural NETWORKs, for research and teaching. Primarily, the book aims to be a quick learning guide for postgraduate/undergraduate students or design engineers interested in learning the fundamentals of modern control of drives and power systems in conjunction with the powerful design methodology based on VHDL.
标签： Neural_and_Fuzzy_Logic_Control
上传时间： 2020-06-10
上传用户：shancjb
The past decade has seen an explosion of machine learning research and appli- cations; especially, deep learning methods have enabled key advances in many applicationdomains,suchas computervision,speechprocessing,andgameplaying. However, the performance of many machine learning methods is very sensitive to a plethora of design decisions, which constitutes a considerable barrier for new users. This is particularly true in the booming field of deep learning, where human engineers need to select the right neural architectures, training procedures, regularization methods, and hyperparameters of all of these components in order to make their NETWORKs do what they are supposed to do with sufficient performance. This process has to be repeated for every application. Even experts are often left with tedious episodes of trial and error until they identify a good set of choices for a particular dataset.
标签： Auto-Machine-Learning-Methods-Sys tems-Challenges
上传时间： 2020-06-10
上传用户：shancjb
The large-scale deployment of the smart grid (SG) paradigm could play a strategic role in supporting the evolution of conventional electrical grids toward active, flexible and self- healing web energy NETWORKs composed of distributed and cooperative energy resources. From a conceptual point of view, the SG is the convergence of information and operational technologies applied to the electric grid, providing sustainable options to customers and improved security. Advances in research on SGs could increase the efficiency of modern electrical power systems by: (i) supporting the massive penetration of small-scale distributed and dispersed generators; (ii) facilitating the integration of pervasive synchronized metering systems; (iii) improving the interaction and cooperation between the network components; and (iv) allowing the wider deployment of self-healing and proactive control/protection paradigms.
标签： Computational Intelligence
上传时间： 2020-06-10
上传用户：shancjb
This book is intended to be a general introduction to neural NETWORKs for those with a computer architecture, circuits, or systems background. In the introduction (Chapter 1), we define key vo- cabulary, recap the history and evolution of the techniques, and for make the case for additional hardware support in the field.
标签： Deep_Learning_for_Computer_Archit ects
上传时间： 2020-06-10
上传用户：shancjb
Computer science as an academic discipline began in the 1960’s. Emphasis was on programming languages, compilers, operating systems, and the mathematical theory that supported these areas. Courses in theoretical computer science covered finite automata, regular expressions, context-free languages, and computability. In the 1970’s, the study of algorithms was added as an important component of theory. The emphasis was on making computers useful. Today, a fundamental change is taking place and the focus is more on a wealth of applications. There are many reasons for this change. The merging of computing and communications has played an important role. The enhanced ability to observe, collect, and store data in the natural sciences, in commerce, and in other fields calls for a change in our understanding of data and how to handle it in the modern setting. The emergence of the web and social NETWORKs as central aspects of daily life presents both opportunities and challenges for theory.
标签： Foundations Science Data of
上传时间： 2020-06-10
上传用户：shancjb
General paradigm in solving a computer vision problem is to represent a raw image using a more informative vector called feature vector and train a classifier on top of feature vectors collected from training set. From classification perspective, there are several off-the-shelf methods such as gradient boosting, random forest and support vector machines that are able to accurately model nonlinear decision boundaries. Hence, solving a computer vision problem mainly depends on the feature extraction algorithm
标签： Convolutional NETWORKs Neural Guide to
上传时间： 2020-06-10
上传用户：shancjb
空天地一体化通信综述，卫星、无人机、地面蜂窝系统协同网络
标签： Satellite-UAV-Vehicle Integrated NETWORKs
上传时间： 2021-10-22
上传用户：yujinsong
5G中的SDN-NFV和云计算.pdf摘 要 通过介绍广义的SDN/NFV和云计算，结合未来5G网络的特点，分析了5G中上述技术的 应用前景和技术定位；结合5G的网络特点和现有网络的部署情况，总结了各技术间的逻辑关系以及运 营商的侧重点。引言 SDN/NFV 和云计算都是起源于 IT 领域的技术。 如今，云计算已经非常成熟，在 IT 领域已经大规模商 用，SDN技术作为新兴的转发技术，也已经被谷歌等互 联网巨头部署在多个数据中心。随着虚 拟化技术的发展，人们试图将更多的专有 设备虚拟化和软件化，从而达到降低成本 和灵活部署的目的，于是 NFV 的概念诞 生了。本文将结合广义上 3 种技术本身 的特点和未来5G的网络能力要求，分析 各技术在5G架构中的技术定位和前景， 同时结合实际的发展情况，总结未来运营 商在技术研发和业务模式上的侧重点。 1.1 广义的SDN及标准化进程 ONF 在 2012 年 4 月 发 布 白 皮 书 《Software- Defined Networking: The New Norm for NETWORKs》
标签： 5G
上传时间： 2022-02-25
上传用户：jason_vip1
摘要：无线传感器网络（Wireless Sensor NETWORKs，wSN是由许多具有低功率无线收发装置的传感器节点组成，它们监测采集周边环境信息并传送到基站进行处理在某一时刻通过wSN采集的数据量非常大，如何正确、高效地处理这些数据成为当前WSN研究中的一个热点。传感器节点一般部署在恶劣环境中，一些偶然因素会使采集的数据中出现不准确的数据，用户依据这样的数据很难准确判断出被测对象的真实状态。基于模糊理论的决策级数据融合算法能够很好的解决这个问题本文以国家863研究项目《基于无线传感器网络的铁路危险货物在途安全状态监测技术研究》为背景，结合铁路运输中棉花在途状态监测系统的开发，在分析了当前有效的决策级数据融合技术基础上，提出了基于模糊理论的决策级数据融合算法，该算法通过对采集数据进行处理和分析，以获得准确的被测对象状态的描述。本文的主要工作包括：（1）分析了WSN中传统的决策级数据融合算法，如自适应加权数据融合算法和算术平均数数据融合算法，总结这两种算法的优缺点和检测系统的需求，进步明确理想算法应达到的目标。（2）提出了基于模糊理论的两阶段数据融合算法：该算法第一阶段利用基于贴近度的数据融合算法进行同类数据的融合校准，这一阶段的目的是剔除错误的和可信度较差的数据，得到相对更加准确的数据，第二阶段利用模糊推理对第个阶段得到的异类数据进行融合推理，得到被测对象当前状态的描述，为决策提供支持（3）结合实测数据仿真本文所提出的算法，结果证明与传统的融合算法相比，可以更加准确的描述被测对象状态
标签： 无线传感器
上传时间： 2022-03-17
上传用户：
随着人类社会的进步，科学技术的发展日新月异，模拟人脑神经网络的人工神经网络已取得了长足的发展。经过半个多世纪的发展，人工神经网络在计算机科学，人工智能，智能控制等方面得到了广泛的应用。当代社会是一个讲究效率的社会，科技更新领域也是如此。在人工神经网络研究领域，算法的优化显得尤为重要，对提高网络整体性能举足轻重.BP神经网络模型是目前应用最为广泛的一种神经网络模型，对于解决非线性复杂问题具有重要的意义。但是BP神经网络有其自身的一些不足（收敛速度慢和容易陷入局部极小值问题），在解决某些现实问题的时候显得力不从心。针对这个问题，本文利用遗传算法的并行全局搜索的优势，能够弥补BP网络的不足，为解决大规模复杂问题提供了广阔的前景。本文将遗传算法与BP网络有机地结合起来，提出了一种新的网络结构，在稳定性、学习性和效率方面都有了很大的提高。基于以上的研究目的，本文首先设计了BP神经网络结构，在此基础上，应用遗传算法进行优化，达到了加快收敛速度和全局寻优的效果。本文借助MATLAB平台，对算法的优化内容进行了仿真实验，得出的效果也符合期望值，实现了对BP算法优化的目的。关键词：生物神经网络：人工神经网络；BP网络；遗传算法；仿真随着电子计算机的问世及发展，人们试图去了解人的大脑，进而构造具有人类思维的智能计算机。在具有人脑逻辑推理延伸能力的计算机战胜人类棋手的同时，引发了人们对模拟人脑信息处理的人工神经网络的研究。1.1研究背景人工神经网络（Artificial Noural NETWORKs，ANN）（注：简称为神经网络），是一种数学算法模型，能够对信息进行分布式处理，它模仿了动物的神经网络，是对动物神经网络的一种具体描述。这种网络依赖系统的复杂程度，通过调节内部大量节点之间的关系，最终实现信息处理的目的。人工神经网络可以通过对输入输出数据的分析学习，掌握输入与输出之间的潜在规则，能够对新数据进行分析计算，推算出输出结果，因为人工神经网络具有自适应和自学习的特性，这种学习适应的过程被称为“训练"。
上传时间： 2022-06-16
上传用户：jiabin
