高階神經網路 的英文怎麼說

中文拼音 [gāojiēshénjīngwǎnglù]
高階神經網路 英文
higher order neural network
  • 高 : Ⅰ形容詞1 （從下向上距離大; 離地面遠） tall; high 2 （在一般標準或平均程度之上; 等級在上的） above...
  • 階 : 名詞1. （臺階） steps; stairs 2. （等級） rank 3. [醫學] （耳蝸的三個螺旋管的任一個） scala 4. [數學] order 5. [地質學] stage
  • 神 : Ⅰ名詞1 （神靈） god; deity; divinity 2 （精神; 精力） spirit; mind 3 （神氣; 神情） expression; l...
  • 經 : 經動詞[紡織] （把紡好的紗或線梳整成經紗或經線） warp
  • 網 : Ⅰ名詞1 （捕魚捉鳥的器具） net 2 （像網的東西） thing which looks like a net 3 （像網一樣的組織或...
  • 路 : 1 （道路） road; way; path 2 （路程） journey; distance 3 （途徑; 門路） way; means 4 （條理） se...
  • 高階 : high [higher] order高階導數 higher derivative; higher order derivative; derivative of higher orde...
  • 神經 : nerve; nervus
  • 網路 : 1. [電學] network; electric network2. （網） meshwork; system; graph （指一維復形）; mesh
  1. The detailed works are as follows : the finding patterns problems in the time - series data sequence are described, and a new trend logic expression method is introduced, and its algorithm and experiment result of algorithm are given ; time - scries data are disposed, and using the arctg. slope of line as the sample of pattern recognition, so ignoring the aberrance of pattern in the classified. in addition, a new time - series pattern finding algorithm based on higher - order neural network is put forward

    同時給出了本文的具體的工作，主要是：對在時序數據序列中發現模式問題進行了描述，並介紹了一種新的趨勢邏輯表示方法，給出了其演算法及演算法的實驗結果；對時序數據進行處理，提出了利用線段的斜率反正切值作為模式識別的樣本，從而在分類時忽略模式的畸變；另外，還提出了一個新的基於高階神經網路的時序模式發現演算法。
  2. This method can reflect local signal feature and well perform in the experiments. we also present an integrated electromyographic signal ( emg ) pattern recognition scheme. the application of an artificial neural network ( ann ) technique together with a feature extraction technique, for the classification of emg signals is described

    利用高階譜技術提取肌電信號的特徵信息，然後利用奇異值或者其它方法對二維特徵矩陣進行優化，將優化之後的一維特徵向量輸入神經網路分類器進行模式識別，這種方法能夠初步識別不同模式的上肢運動。
  3. 5. in step current detection, intelligent pattern recognition capacity of artificial neural networks is utilized, then man - made factors are eliminated during judging the quality of pipeline coating, as well as avoiding numerous iterant calculations in curve imitation. therefore, the speed of judging coating quality is accelerated greatly

    在恆電流階躍激勵檢測中，利用了人工神經網路的智能模式識別的能力，使得在管道塗層狀態判斷中消除了人為因素，同時避免了曲線擬合中的大量重復性計算，大大提高了塗層狀態判斷的速度。
  4. Many new methods, such as reduction of gravity data to a horizontal plane, wavelet analysis, higher order statistics, joint inversion and interactive inversion of gravity, magnetic, electric and seismic data, 3 - d visualized inversion, as well as bp artificial network method have been widely used in the integrated data processing

    山區重力資料曲化平，小波分析及高階統計量等現代信號處理方法，重震、重磁、電震的聯合反演與交互反演，三維可視化反演， bp人工神經網路方法等在綜合地球物理處理解釋中得到廣泛應用。
  5. 3. the modeling method based on mechanism analysis and identification method always exits unmodeled high - order part and the modeling method based on neural networks usually has not good enough generalization capability. we fuse above two kinds of modeling method and put forward a hybrid modeling method based on mechanism analysis, identification and rbf neural networks. this paper proposed a hybr id modeling method based on mechanism analysis, identification and rbf neural networks. first, get a object ' s low - order model by the mechanism analysis and identification method. second, adopt rbf neural networks modeling method to compensate unmodeled high - order model. the sum of the low - order model and high - order model is the hybrid model. this kind of hybrid model has more accuracy than a model based on mechanism analysis and identification and has more generalization capability than a model based on neural networks

    針對基於機理分析和辨識的建模方法總是存在未建模的高階部分，精度不夠高和神經網路建模方法泛化能力差的缺點，將這兩種建模方法進行融合，提出基於機理分析、系統辨識和rbf神經網路的混合建模方法，首先採用機理分析和辨識的方法得到工業對象的低階模型，再用rbf神經網路建模方法補償未建模高階模型，這樣得到的混合模型，比單純基於機理分析和辨識的建模方法具有更高的精度，比單純的神經網路的建模方法具有更好的泛化能力。
  6. Based on the practical condition of the heating distribution network in beijing city, this paper systematically discusses the application of the neural network in the field of heating burden prediction and dispatching, include : based on city heating system, systematically analyzing the current condition of the heating system in our city and the development of the international heating technique, discussing the tendency in the field of the domestic heating system. at the same time, constructing a heating model characterized by distribution, ranking structure, intelligentized and favorable practicability and reliability, which adapts to the situation of our city and greatly enhances the level of automation and energy saving

    本文從北京市供熱管網的實際出發，系統地討論了適合我市實情的神經網路技術在供熱管網預測和調度中的應用研究，主要進行了如下幾個方面的工作：以城市供熱系統為對象，綜合分析了我市集中供熱的現狀，結合當前國際供熱技術的發展，分析了我市集中供熱的發展趨勢，並提出了一種適合我市實情的供熱模型，該模型具有分散式、遞階結構、智能化以及良好的實用性和可靠性等特點，可極大提高集中供熱的自動化水平和節能效果。
  7. This dissertation presented two new methods of robust adaptive track control for a class of mimo strong nonlinear system with external disturbance. one method makes use of taylor approximation principle to linearize the mimo strong nonlinear system at the ideal equilibrium point, meanwhile external disturbance is considered, and then designs two on - line neural network controller respectively, which can dynamically compensate the high order items of taylor series and the control signals at ideal equilibrium point under the drive of state error between linear and nonlinear system. a linear feedback controller obtained by pole assignment and two on - line neural network act on the practical mimo high nonlinear system together, guaranteeing the whole system robust stable and tracking the specified signal ; the other method designs three on - line neural networks for this class of system

    本文對於一類含有外部擾動的多輸入多輸出（ mimo ）強非線性系統，提出了兩種新的魯棒自適應跟蹤控制方法，第一種利用了taylor近似的原理，在考慮了外部擾動的情況下，將mimo強非線性系統在理想平衡點處線性化，分別設計了兩個在線神經網路控制器，在線性和非線性系統之間的狀態誤差驅動下動態補償系統的taylor近似高階項及理想平衡點處的控制信號，滿足極點配置方法的線性反饋控制器和兩個在線神經網路聯合作用於實際的被控mimo強非線性系統，在保證整個系統魯棒穩定性的情況下，能夠跟蹤給定的指令信號；另一種方法是針對這類系統設計了3個在線神經網路，分別實時抵消這類非線性系統中的非線性部分、與控制量耦合的非線性項以及外部擾動，使得受控系統的輸出可以完全跟蹤給定輸入參考信號。
  8. Aiming at the control feature of large ship, the authors designed a 2 - rank derivative multi - step neural network predictive model and the algorithm of the large delay ship ' s course, and presented a fuzzy control autopilot scheme based on the model with rbf neural network and fcmac controller, it solved problems of model online identification and controller online design in traditional adaptive control, so that the high precision output follow - up control of large ship with large delay and uncertain nonlinear features can be realized

    摘要針對大型船舶控制特性，設計了船舶航向的神經網路二階導數多步預測模型及其辨識和預測演算法，提出基於徑向基函數神經網路多步預測模型和模糊小腦模型關節神經網路控制器的大時滯船舶航向模糊控制自動舵方案，解決傳統自適應控制中模型的在線辨識和控制器的在線設計問題，以達到對具有大時滯、不確定非線性特性的大型船舶實現高精度輸出跟蹤控制。
  9. This paper presents a model of cosine basis functions neural network based on bp algorithm, discusses the relation between the algorithm of neural network and amplitude - frequency characteristic about the linear phase fir filter, introduces the convergence condition of neural network algorithm, and studies the optimal design example about the high - order fir double - band - pass filters

    提出了一種基於bp演算法的正弦基函數神經網路模型及演算法的收斂條件，研究了該神經網路演算法與fir線性相位濾波器幅頻特性的關系，給出了高階雙通帶濾波器的優化設計實例。
  10. The main results are as follows. firstly, for a class of unknown nonlinear high - order system, the neural network is introduced into ilc. the ilc is incorporated with the adaptive control to achieve arbitrary tracking accuracy

    本文的主要工作包括以下幾個方面：第一，對一類未知非線性高階系統，將神經網路引入迭代學習控制，迭代學習控制與自適應控制相結合，實現了任意精度的跟蹤。
  11. In this paper, we analyze the statistic characters of time - delay in detail, and put forward to adopt elman nn to forecast time - delay intelligently, design appropriate compensator based on adaptive smith forecast theory. the experiment results prove that this method can improve the forecast accuracy and system ' s dynamic performance. in the application of real time data transmission, forward error correction ( fec ) is a good method to resume the lost data

    針對這個問題本文進行了詳盡的統計特性分析，並且提出採用elman動態神經網路結構對網路時延進行智能預測，並根據自適應smith預估補償控制原理設計合適的時延補償器，並且應用於基於web的二階水位控制系統中，實驗結果證明了採用此方法可以提高預測精度，使時延補償器適應時延變化的動態性更強，從而在保證系統穩定性的基礎上，西安理工大學碩士學位論文提高系統的時延補償精度。
  12. Research on higher - order neural networks

    高階神經網路模型特性研究
  13. In this algorithm, author used two technology - the higher - order neural network of single _ layer and hierarchy

    在這一演算法中，作者運用了單層的高階神經網路和分層方法。
  14. The paper studies the existence and global exponential convergence of alomost periodic solutions for high - order neural networks involving variable delay by applying the theory of fixed point and differential inequality technique, some new criteria on the existence and global exponential convergence of almost periodic solutions are obtained

    摘要利用不動點理論和微分不等式分析等技巧，研究了變時滯高階神經網路概周期解存在性與全局指數收斂性，並且給出了一些新的判別準則。
  15. Comparing with the other time - series pattern finding algorithm, this one has a few of innovations. firstly, improving time - series pattern finding algorithm from the classified accuracy. secondly, ignoring some aberrance of time - series pattern by the high - order neural network

    同其他的時序模式發現演算法相比較，具有幾點創新： 1 ）從分類精度的角度來改善時序模式發現演算法； 2 ）通過高階神經網路，直接利用網路的特性忽略了時序模式的某些畸變； 3 ）利用了分層方法，進一步改善分類精度。
  16. Higher - order neural network of single _ layer has no trouble of hiding layer node, so training speed is fast ; ability of pattern classified increases ; the classification accuracy of pattern is improved without local optimality problem ; hierarchy can make training speed of each node neural network, and improve the classified accuracy of pattern

    單層高階神經網路沒有隱含層節點的困擾，訓練速度更快；模式分類能力更為強大；不存在局部最小的問題，模式分類精度更高；模式的不變性構建於網路結構之中等優點。分層方法能加快各節點神經網路的學習速度，也能提高模式劃分精度。
分享友人
分享到 Line

分享到臉書