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.
標簽： Neural_and_Fuzzy_Logic_Control
上傳時間： 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.
標簽： Auto-Machine-Learning-Methods-Sys tems-Challenges
上傳時間： 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.
標簽： Computational Intelligence
上傳時間： 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.
標簽： Deep_Learning_for_Computer_Archit ects
上傳時間： 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.
標簽： Foundations Science Data of
上傳時間： 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
標簽： Convolutional NETWORKS Neural Guide to
上傳時間： 2020-06-10
上傳用戶：shancjb
空天地一體化通信綜述，衛(wèi)星、無人機、地面蜂窩系統(tǒng)協(xié)同網(wǎng)絡
標簽： Satellite-UAV-Vehicle Integrated NETWORKS
上傳時間： 2021-10-22
上傳用戶：yujinsong
5G中的SDN-NFV和云計算.pdf摘 要 通過介紹廣義的SDN/NFV和云計算，結合未來5G網(wǎng)絡的特點，分析了5G中上述技術的 應用前景和技術定位；結合5G的網(wǎng)絡特點和現(xiàn)有網(wǎng)絡的部署情況，總結了各技術間的邏輯關系以及運 營商的側(cè)重點。引言 SDN/NFV 和云計算都是起源于 IT 領域的技術。 如今，云計算已經(jīng)非常成熟，在 IT 領域已經(jīng)大規(guī)模商 用，SDN技術作為新興的轉(zhuǎn)發(fā)技術，也已經(jīng)被谷歌等互 聯(lián)網(wǎng)巨頭部署在多個數(shù)據(jù)中心。隨著虛 擬化技術的發(fā)展，人們試圖將更多的專有 設備虛擬化和軟件化，從而達到降低成本 和靈活部署的目的，于是 NFV 的概念誕 生了。本文將結合廣義上 3 種技術本身 的特點和未來5G的網(wǎng)絡能力要求，分析 各技術在5G架構中的技術定位和前景， 同時結合實際的發(fā)展情況，總結未來運營 商在技術研發(fā)和業(yè)務模式上的側(cè)重點。 1.1 廣義的SDN及標準化進程 ONF 在 2012 年 4 月 發(fā) 布 白 皮 書 《Software- Defined Networking: The New Norm for NETWORKS》
標簽： 5G
上傳時間： 2022-02-25
上傳用戶：jason_vip1
摘要：無線傳感器網(wǎng)絡（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)點組成，它們監(jiān)測采集周邊環(huán)境信息并傳送到基站進行處理在某一時刻通過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)成為當前WSN研究中的一個熱點。傳感器節(jié)點一般部署在惡劣環(huán)境中，一些偶然因素會使采集的數(shù)據(jù)中出現(xiàn)不準確的數(shù)據(jù)，用戶依據(jù)這樣的數(shù)據(jù)很難準確判斷出被測對象的真實狀態(tài)。基于模糊理論的決策級數(shù)據(jù)融合算法能夠很好的解決這個問題本文以國家863研究項目《基于無線傳感器網(wǎng)絡的鐵路危險貨物在途安全狀態(tài)監(jiān)測技術研究》為背景，結合鐵路運輸中棉花在途狀態(tài)監(jiān)測系統(tǒng)的開發(fā)，在分析了當前有效的決策級數(shù)據(jù)融合技術基礎上，提出了基于模糊理論的決策級數(shù)據(jù)融合算法，該算法通過對采集數(shù)據(jù)進行處理和分析，以獲得準確的被測對象狀態(tài)的描述。本文的主要工作包括：（1）分析了WSN中傳統(tǒng)的決策級數(shù)據(jù)融合算法，如自適應加權數(shù)據(jù)融合算法和算術平均數(shù)數(shù)據(jù)融合算法，總結這兩種算法的優(yōu)缺點和檢測系統(tǒng)的需求，進步明確理想算法應達到的目標。（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)融合算法進行同類數(shù)據(jù)的融合校準，這一階段的目的是剔除錯誤的和可信度較差的數(shù)據(jù)，得到相對更加準確的數(shù)據(jù)，第二階段利用模糊推理對第個階段得到的異類數(shù)據(jù)進行融合推理，得到被測對象當前狀態(tài)的描述，為決策提供支持（3）結合實測數(shù)據(jù)仿真本文所提出的算法，結果證明與傳統(tǒng)的融合算法相比，可以更加準確的描述被測對象狀態(tài)
標簽： 無線傳感器
上傳時間： 2022-03-17
上傳用戶：
隨著人類社會的進步，科學技術的發(fā)展日新月異，模擬人腦神經(jīng)網(wǎng)絡的人工神經(jīng)網(wǎng)絡已取得了長足的發(fā)展。經(jīng)過半個多世紀的發(fā)展，人工神經(jīng)網(wǎng)絡在計算機科學，人工智能，智能控制等方面得到了廣泛的應用。當代社會是一個講究效率的社會，科技更新領域也是如此。在人工神經(jīng)網(wǎng)絡研究領域，算法的優(yōu)化顯得尤為重要，對提高網(wǎng)絡整體性能舉足輕重.BP神經(jīng)網(wǎng)絡模型是目前應用最為廣泛的一種神經(jīng)網(wǎng)絡模型，對于解決非線性復雜問題具有重要的意義。但是BP神經(jīng)網(wǎng)絡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)實問題的時候顯得力不從心。針對這個問題，本文利用遺傳算法的并行全局搜索的優(yōu)勢，能夠彌補BP網(wǎng)絡的不足，為解決大規(guī)模復雜問題提供了廣闊的前景。本文將遺傳算法與BP網(wǎng)絡有機地結合起來，提出了一種新的網(wǎng)絡結構，在穩(wěn)定性、學習性和效率方面都有了很大的提高。基于以上的研究目的，本文首先設計了BP神經(jīng)網(wǎng)絡結構，在此基礎上，應用遺傳算法進行優(yōu)化，達到了加快收斂速度和全局尋優(yōu)的效果。本文借助MATLAB平臺，對算法的優(yōu)化內(nèi)容進行了仿真實驗，得出的效果也符合期望值，實現(xiàn)了對BP算法優(yōu)化的目的。關鍵詞：生物神經(jīng)網(wǎng)絡：人工神經(jīng)網(wǎng)絡；BP網(wǎng)絡；遺傳算法；仿真隨著電子計算機的問世及發(fā)展，人們試圖去了解人的大腦，進而構造具有人類思維的智能計算機。在具有人腦邏輯推理延伸能力的計算機戰(zhàn)勝人類棋手的同時，引發(fā)了人們對模擬人腦信息處理的人工神經(jīng)網(wǎng)絡的研究。1.1研究背景人工神經(jīng)網(wǎng)絡（Artificial Noural NETWORKS，ANN）（注：簡稱為神經(jīng)網(wǎng)絡），是一種數(shù)學算法模型，能夠?qū)π畔⑦M行分布式處理，它模仿了動物的神經(jīng)網(wǎng)絡，是對動物神經(jīng)網(wǎng)絡的一種具體描述。這種網(wǎng)絡依賴系統(tǒng)的復雜程度，通過調(diào)節(jié)內(nèi)部大量節(jié)點之間的關系，最終實現(xiàn)信息處理的目的。人工神經(jīng)網(wǎng)絡可以通過對輸入輸出數(shù)據(jù)的分析學習，掌握輸入與輸出之間的潛在規(guī)則，能夠?qū)π聰?shù)據(jù)進行分析計算，推算出輸出結果，因為人工神經(jīng)網(wǎng)絡具有自適應和自學習的特性，這種學習適應的過程被稱為“訓練"。
標簽： 遺傳算法 bp神經(jīng)網(wǎng)絡 matlab
上傳時間： 2022-06-16
上傳用戶：jiabin
