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.
標(biāo)簽： Neural_and_Fuzzy_Logic_Control
上傳時(shí)間： 2020-06-10
上傳用戶：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.
標(biāo)簽： Auto-Machine-Learning-Methods-Sys tems-Challenges
上傳時(shí)間： 2020-06-10
上傳用戶：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.
標(biāo)簽： Computational Intelligence
上傳時(shí)間： 2020-06-10
上傳用戶：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.
標(biāo)簽： Deep_Learning_for_Computer_Archit ects
上傳時(shí)間： 2020-06-10
上傳用戶：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.
標(biāo)簽： Foundations Science Data of
上傳時(shí)間： 2020-06-10
上傳用戶：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
標(biāo)簽： Convolutional netWorks Neural Guide to
上傳時(shí)間： 2020-06-10
上傳用戶：shancjb
空天地一體化通信綜述，衛(wèi)星、無人機(jī)、地面蜂窩系統(tǒng)協(xié)同網(wǎng)絡(luò)
標(biāo)簽： Satellite-UAV-Vehicle Integrated netWorks
上傳時(shí)間： 2021-10-22
上傳用戶：yujinsong
5G中的SDN-NFV和云計(jì)算.pdf摘 要 通過介紹廣義的SDN/NFV和云計(jì)算，結(jié)合未來5G網(wǎng)絡(luò)的特點(diǎn)，分析了5G中上述技術(shù)的 應(yīng)用前景和技術(shù)定位；結(jié)合5G的網(wǎng)絡(luò)特點(diǎn)和現(xiàn)有網(wǎng)絡(luò)的部署情況，總結(jié)了各技術(shù)間的邏輯關(guān)系以及運(yùn) 營(yíng)商的側(cè)重點(diǎn)。引言 SDN/NFV 和云計(jì)算都是起源于 IT 領(lǐng)域的技術(shù)。 如今，云計(jì)算已經(jīng)非常成熟，在 IT 領(lǐng)域已經(jīng)大規(guī)模商 用，SDN技術(shù)作為新興的轉(zhuǎn)發(fā)技術(shù)，也已經(jīng)被谷歌等互 聯(lián)網(wǎng)巨頭部署在多個(gè)數(shù)據(jù)中心。隨著虛 擬化技術(shù)的發(fā)展，人們?cè)噲D將更多的專有 設(shè)備虛擬化和軟件化，從而達(dá)到降低成本 和靈活部署的目的，于是 NFV 的概念誕 生了。本文將結(jié)合廣義上 3 種技術(shù)本身 的特點(diǎn)和未來5G的網(wǎng)絡(luò)能力要求，分析 各技術(shù)在5G架構(gòu)中的技術(shù)定位和前景， 同時(shí)結(jié)合實(shí)際的發(fā)展情況，總結(jié)未來運(yùn)營(yíng) 商在技術(shù)研發(fā)和業(yè)務(wù)模式上的側(cè)重點(diǎn)。 1.1 廣義的SDN及標(biāo)準(zhǔn)化進(jìn)程 ONF 在 2012 年 4 月 發(fā) 布 白 皮 書 《Software- Defined Networking: The New Norm for netWorks》
標(biāo)簽： 5G
上傳時(shí)間： 2022-02-25
上傳用戶：jason_vip1
摘要：無線傳感器網(wǎng)絡(luò)（Wireless Sensor netWorks，wSN是由許多具有低功率無線收發(fā)裝置的傳感器節(jié)點(diǎn)組成，它們監(jiān)測(cè)采集周邊環(huán)境信息并傳送到基站進(jìn)行處理在某一時(shí)刻通過wSN采集的數(shù)據(jù)量非常大，如何正確、高效地處理這些數(shù)據(jù)成為當(dāng)前WSN研究中的一個(gè)熱點(diǎn)。傳感器節(jié)點(diǎn)一般部署在惡劣環(huán)境中，一些偶然因素會(huì)使采集的數(shù)據(jù)中出現(xiàn)不準(zhǔn)確的數(shù)據(jù)，用戶依據(jù)這樣的數(shù)據(jù)很難準(zhǔn)確判斷出被測(cè)對(duì)象的真實(shí)狀態(tài)。基于模糊理論的決策級(jí)數(shù)據(jù)融合算法能夠很好的解決這個(gè)問題本文以國(guó)家863研究項(xiàng)目《基于無線傳感器網(wǎng)絡(luò)的鐵路危險(xiǎn)貨物在途安全狀態(tài)監(jiān)測(cè)技術(shù)研究》為背景，結(jié)合鐵路運(yùn)輸中棉花在途狀態(tài)監(jiān)測(cè)系統(tǒng)的開發(fā)，在分析了當(dāng)前有效的決策級(jí)數(shù)據(jù)融合技術(shù)基礎(chǔ)上，提出了基于模糊理論的決策級(jí)數(shù)據(jù)融合算法，該算法通過對(duì)采集數(shù)據(jù)進(jìn)行處理和分析，以獲得準(zhǔn)確的被測(cè)對(duì)象狀態(tài)的描述。本文的主要工作包括：（1）分析了WSN中傳統(tǒng)的決策級(jí)數(shù)據(jù)融合算法，如自適應(yīng)加權(quán)數(shù)據(jù)融合算法和算術(shù)平均數(shù)數(shù)據(jù)融合算法，總結(jié)這兩種算法的優(yōu)缺點(diǎn)和檢測(cè)系統(tǒng)的需求，進(jìn)步明確理想算法應(yīng)達(dá)到的目標(biāo)。（2）提出了基于模糊理論的兩階段數(shù)據(jù)融合算法：該算法第一階段利用基于貼近度的數(shù)據(jù)融合算法進(jìn)行同類數(shù)據(jù)的融合校準(zhǔn)，這一階段的目的是剔除錯(cuò)誤的和可信度較差的數(shù)據(jù)，得到相對(duì)更加準(zhǔn)確的數(shù)據(jù)，第二階段利用模糊推理對(duì)第個(gè)階段得到的異類數(shù)據(jù)進(jìn)行融合推理，得到被測(cè)對(duì)象當(dāng)前狀態(tài)的描述，為決策提供支持（3）結(jié)合實(shí)測(cè)數(shù)據(jù)仿真本文所提出的算法，結(jié)果證明與傳統(tǒng)的融合算法相比，可以更加準(zhǔn)確的描述被測(cè)對(duì)象狀態(tài)
標(biāo)簽： 無線傳感器
上傳時(shí)間： 2022-03-17
上傳用戶：
隨著人類社會(huì)的進(jìn)步，科學(xué)技術(shù)的發(fā)展日新月異，模擬人腦神經(jīng)網(wǎng)絡(luò)的人工神經(jīng)網(wǎng)絡(luò)已取得了長(zhǎng)足的發(fā)展。經(jīng)過半個(gè)多世紀(jì)的發(fā)展，人工神經(jīng)網(wǎng)絡(luò)在計(jì)算機(jī)科學(xué)，人工智能，智能控制等方面得到了廣泛的應(yīng)用。當(dāng)代社會(huì)是一個(gè)講究效率的社會(huì)，科技更新領(lǐng)域也是如此。在人工神經(jīng)網(wǎng)絡(luò)研究領(lǐng)域，算法的優(yōu)化顯得尤為重要，對(duì)提高網(wǎng)絡(luò)整體性能舉足輕重.BP神經(jīng)網(wǎng)絡(luò)模型是目前應(yīng)用最為廣泛的一種神經(jīng)網(wǎng)絡(luò)模型，對(duì)于解決非線性復(fù)雜問題具有重要的意義。但是BP神經(jīng)網(wǎng)絡(luò)有其自身的一些不足（收斂速度慢和容易陷入局部極小值問題），在解決某些現(xiàn)實(shí)問題的時(shí)候顯得力不從心。針對(duì)這個(gè)問題，本文利用遺傳算法的并行全局搜索的優(yōu)勢(shì)，能夠彌補(bǔ)BP網(wǎng)絡(luò)的不足，為解決大規(guī)模復(fù)雜問題提供了廣闊的前景。本文將遺傳算法與BP網(wǎng)絡(luò)有機(jī)地結(jié)合起來，提出了一種新的網(wǎng)絡(luò)結(jié)構(gòu)，在穩(wěn)定性、學(xué)習(xí)性和效率方面都有了很大的提高。基于以上的研究目的，本文首先設(shè)計(jì)了BP神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)，在此基礎(chǔ)上，應(yīng)用遺傳算法進(jìn)行優(yōu)化，達(dá)到了加快收斂速度和全局尋優(yōu)的效果。本文借助MATLAB平臺(tái)，對(duì)算法的優(yōu)化內(nèi)容進(jìn)行了仿真實(shí)驗(yàn)，得出的效果也符合期望值，實(shí)現(xiàn)了對(duì)BP算法優(yōu)化的目的。關(guān)鍵詞：生物神經(jīng)網(wǎng)絡(luò)：人工神經(jīng)網(wǎng)絡(luò)；BP網(wǎng)絡(luò)；遺傳算法；仿真隨著電子計(jì)算機(jī)的問世及發(fā)展，人們?cè)噲D去了解人的大腦，進(jìn)而構(gòu)造具有人類思維的智能計(jì)算機(jī)。在具有人腦邏輯推理延伸能力的計(jì)算機(jī)戰(zhàn)勝人類棋手的同時(shí)，引發(fā)了人們對(duì)模擬人腦信息處理的人工神經(jīng)網(wǎng)絡(luò)的研究。1.1研究背景人工神經(jīng)網(wǎng)絡(luò)（Artificial Noural netWorks，ANN）（注：簡(jiǎn)稱為神經(jīng)網(wǎng)絡(luò)），是一種數(shù)學(xué)算法模型，能夠?qū)π畔⑦M(jìn)行分布式處理，它模仿了動(dòng)物的神經(jīng)網(wǎng)絡(luò)，是對(duì)動(dòng)物神經(jīng)網(wǎng)絡(luò)的一種具體描述。這種網(wǎng)絡(luò)依賴系統(tǒng)的復(fù)雜程度，通過調(diào)節(jié)內(nèi)部大量節(jié)點(diǎn)之間的關(guān)系，最終實(shí)現(xiàn)信息處理的目的。人工神經(jīng)網(wǎng)絡(luò)可以通過對(duì)輸入輸出數(shù)據(jù)的分析學(xué)習(xí)，掌握輸入與輸出之間的潛在規(guī)則，能夠?qū)π聰?shù)據(jù)進(jìn)行分析計(jì)算，推算出輸出結(jié)果，因?yàn)槿斯ど窠?jīng)網(wǎng)絡(luò)具有自適應(yīng)和自學(xué)習(xí)的特性，這種學(xué)習(xí)適應(yīng)的過程被稱為“訓(xùn)練"。
標(biāo)簽： 遺傳算法 bp神經(jīng)網(wǎng)絡(luò) matlab
上傳時(shí)間： 2022-06-16
上傳用戶：jiabin
蟲蟲下載站版權(quán)所有 京ICP備2021023401號(hào)-1
<font id="dmxou"></font>