神經計算學 的英文怎麼說

中文拼音 [shénjīngjìsuànxué]
神經計算學 英文
neural computing
  • 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
  • 計 : Ⅰ動詞1 （計算） count; compute; calculate; number 2 （設想; 打算） plan; plot Ⅱ名詞1 （測量或計算...
  • 算 : Ⅰ動詞1 （計算數目） calculate; reckon; compute; figure 2 （計算進去） include; count 3 （謀劃;計...
  • 學 : Ⅰ動詞1 （學習） study; learn 2 （模仿） imitate; mimic Ⅱ名詞1 （學問） learning; knowledge 2 （學...
  • 神經 : nerve; nervus
  • 計算 : 1 （求得未知數） count; compute; calculate; reckon; enumerate 2 （考慮; 籌劃） consideration; pla...
  1. Thirdly, resorting to cooperation - competition model of biomathematics, this thesis proposes a new co - evolution model. simulation results are shown to verify its effect and practicabilitv. last, standard methods for optimizing neural netvvorks are easily trapped into local optimization, and unable to adjust the structure of neural networks, thus their application is limited to certain extent

    本文主要驗證和設計適應性操作運算元和小生境方法保持群體多樣性的能力，實驗表明兩種方法都能較好地達到目的；利用生物合作競爭模型設計協同演化來動態地改變群體規模，實驗表明該模型是有效的；人工神經網路是得到越來越廣泛應用的學習系統，但是由於學習演算法存在一定的缺陷，如易於陷入局部極值，難以調整網路的結構等，使神經網路的應用受到一定的限制。
  2. For most of its 100 - year history, neuroscience has embraced a central dogma : a mature adult ' s brain remains a stable, unchanging, computerlike machine with fixed memory and processing power

    神經科學100年的歷史當中，大多信奉著一個中心思想：成年人的腦子是個穩定、不變、如計算機般的機器，有著一成不變的記憶與資訊處理能力。
  3. Livingstone d j, manallack d t, tekto i v. data modeling with neural networks : adventages and limitations [ j ]. comput aided mol design, 1997 ( 135 ) : 11

    閻平凡，張長水.人工神經網路與模擬進化計算[ m ] .北京:清華大學出版社， 2000
  4. Firstly, second harmonic component ratio and dead angles of two phase inrush ' s dispersion in three - phase transformes are acted as input variable. secondly, the method applies improved algorithm based on the original algorithm of multi - layer forward back propagation network, that is to say, adding last variational effect of weight value and bias value to this time and making use of variable learning rate. at the same time, this method also adopts dynamic form in the number of hidden floor node

    首先，文中將三相變壓器兩相涌流差流的二次諧波含量比和間斷角作為網路的輸入變量；其次，利用對原有bp網路訓練演算法基礎上的改進型演算法（即在計算本次權值和閾值的變化時增加上一次權值和閾值變化的影響以及採用變學習率，與此同時隱含層神經元個數採用動態形式） ，通過樣本訓練使網路結構模型達到最優。
  5. The urban traffic trunk is regarded as a large system, and the subsystems are the intersections in the trunk. then we desipi a two - level coordinated fuzzy control method and use ann to implement the fuzzification, fuzzy inference and defuzzification. the arithmetic homs the strongly self - adapt, self - learning and fault - tolerant function

    3 ）把城市交通干線作為一個大系統，子系統為干線上的各個交叉口，在此基礎上，設計了一種城市交通干線的兩級模糊協調控制演算法，並用bp神經網路實現控制器的模糊化、模糊推理和清晰化三個部分，系統具有較強的自適應、自學習和容錯性。
  6. In this paper, the rotating machinery at high speed is studied. there are discussed about numerical calculating methods for non - linear dynamical system, the rotor system radial impact and rubbing dynamics behavior analysis having the nonlinear rigidity on the unsteady and non - linear oil film, the rotor system dynamics behavior analysis with bending - torsional - pendular coupling vibrations, application of wavelet, fractal and network in fault diagnosis. the main works in this paper are as follows : ( 1 )

    本文以高速旋轉機械為主要研究對象，系統、深入地研究了非線性動力學系統的數值計算方法、具有非線性剛度的轉子系統在非穩態非線性油膜力作用下的徑向碰摩動力學行為、轉子彎扭擺耦合振動的動力學分析、小波和分形理論及人工神經網路在故障診斷中的應用問題。
  7. Based on the recent finding on biovision, this paper made a detailed research on the motion biovision model. how biovision system to percept motion and motion form is the topic in this paper

    本論文在國際上生物視覺的新近研究成果的基礎上，對運動生物視覺機制進行了神經動力學建模和計算機模擬的研究。
  8. The innovations of this thesis can be summarized into three points. firstly, the average relative velocity is introducd into a novel adptive weighted clustering algorithm as one important parameter of weight, then it increases the stability and self - adaptability of cluster head. secondly, a new approach to calculating weight is suggested by integrating subjective and objective factors. it is verified by comparison with other approaches to selecting weight. thus the velocity of weight responding to the changes of network topology is increased. finally, using a som neural network to create a classifying model enables every node to learn to identify by itself the role in manet

    本文的創新點有三個:首先本文在wca和aow分簇演算法的基礎上，引入了平均相對移動速度作為權值重要的參數，提出了一種新的基於權值的自適應分簇演算法，提高了簇頭在移動中的穩定性和自適應性;其次，提出了利用主客觀綜合賦權法確定權重的權值計算方法，通過與其他權重選擇方法比較，網路結構變化的權值響應速度得到了改進;最後，論文利用自組織特徵映射神經網路建立分類模型，使得網路中的節點可以自學習地確定簇中角色。
  9. Neural network control is an important mode of intelligent control, and it is widely used in branches of control science, first, the architecture and the learning rule ( error back propagation algorithm ) of multiplayered neural network which is widely used in control system are presentedo especially, the paper refers to the architecture of diagonal recurrent neural network and its learning algorithm - - - - - recurrent prediction error algorithm because of its faster convergence with low computing costo next, before introducing the neural network control to the double close loop dc driver system, the controllers of current and velocity loop are designed using engineering design approach after analysis of the system, simulation models of the system are created

    神經網路控制是智能控制的重要方式之一，它廣泛應用於自動控制學科各個領域。本文首先敘述了控制系統中常用的多層前饋網路結構及演算法（ bp演算法） ，特別提及了能夠較好描述系統動態性能的對角遞歸神經網路和在用遞推預報誤差演算法訓練drnn時取得了較快的收斂速度。其次，應用工程方法分析設計了tf - 1350糖分離機的電流、轉速雙閉環直流調速系統的控制器，作為引入神經網路控制的設計基礎，並建立了系統的模擬模型。
  10. It is very important to estimate the basic parameters in helicopter preliminary design. neural network ( nn ) has the advantages in estimating accuracy and generalization over traditional methods. however, there are some difficulties in using nn, e. g., how to select a proper network structure and the number of hidden layers. in this paper, structure and connection weight of a three - layer nn are optimized by genetic algorithm, and the optimized network is applied to helicopter sizing. the proposed method can not only give an optimal nn structure and connection weight, but also reduce the prediction error and has the capability of self - learning when the latest data are available. furthermore, this method can be easily applied to helicopter design systems

    在直升機初步設計階段估算其基本參數是很重要的.神經網路的通用性和精度比傳統的估算方法有更多的優勢，但是在應用神經網路時存在如何選擇合適的網路結構和隱層節點數目等一些困難.應用遺傳演算法優化三層神經網路結構和連接權重，並將優化得到的網路應用於直升機參數選擇中.該方法不但可以給出一個最優的神經網路結構和連接權重，而且降低了估算誤差，具有及時應用最新數據學習的能力.此外，該方法易於在直升機設計系統中得到應用
  11. In the algorithm level, currently various training algorithms of neural networks, including gradient algorithms, intelligent learning algorithms and hybrid algorithms, are comparatively studied ; the optimization principle of bp algorithm for neural networks training is analyzed in detail, and the reasons for serious disadvantages of bp algorithms are found out, moreover, the optimization principle of two kinds of improved bp algorithms is described in a uniform theoretic framework ; and the global optimization algorithms of neural networks, mainly genetic algorithm are expounded in detail, it follows that a improved genetic algorithm is proposed ; finally the training performances of various algorithms are compared based on a simulation experiment on a benchmark problem of neural network learning, furthermore, a viewpoint that genetic algorithm is subject to " curse of dimension " is proposed

    在演算法層，本文對目前用於神經網路訓練的各種演算法，包括梯度演算法、智能學習演算法和混合學習演算法進行了比較研究；對用於神經網路訓練的bp演算法的優化原理進行了詳細的理論分析，找到了bp演算法存在嚴重缺陷的原因，並對其兩類改進演算法-啟發式演算法和二次梯度演算法的優化原理，在統一的框架之下進行了詳盡的理論描述；對神經網路全局優化演算法主要是遺傳演算法進行了詳細的闡述，並在此基礎上，設計了一種性能改進的遺傳演算法；最後基於神經網路學習的benchmark問題對各種演算法在網路訓練中的應用性能進行了模擬研究，並提出了遺傳演算法受困於「維數災難」的觀點。
  12. In the usa researchers work on psychotronic effect and employ oriental psychophysical systems, hypnosis, neurolinguistic programming, computer psychotechnologies and bio - resonance stimulation in their studies

    在美國，研究人員研究精神電子作用，在研究中採用東方的精神物理學系統，催眠，神經語言學編程，計算機工程心理學和生物共振刺激。
  13. After a 15 - minute digestive period, participants completed a variety of computer - based neuropsychological tests designed to assess cognitive performance including memory, attention span, reaction time, and problem solving ability

    經過15分鐘的消化后，志願者們完成了一系列神經心理學的計算機測試，這些測試旨在對他們的記憶力、注意力持久度、反應時間以及解決問題能力等認知表現進行評估。
  14. Exploration of the convergence of theoretical work and experimental data on neuronal computations that highlight the feedback requirement for the systematic operation of the nervous system

    集中探討了神經計算科學的理論工作和實驗數據，特別討論了神經系統進行系統性運作時反饋的必要性。
  15. The fuzzy system is constructed through the artificial neural learning algorithm. third, the fault diagnosis using neural networks is discussed in this paper, especially the internal backward neural network with deviation elements. its model and learning algorithm are showed in detail

    其中詳細討論了帶有偏差單元的遞歸神經網路的模型和學習演算法，在此基礎上合成了模糊神經網路系統，將模糊理論和神經計算原理相結合，使神經網路藉助其大規模的并行分佈處理結構完成模糊診斷的推理過程。
  16. It begins form the discussion the knowledge of the gaussian filter and the laplacian operator, which are the base of the marr method. and it is followed by the detail discussion of such as : the 2g （ laplacian of gaussian ) filter, the template log ( laplacian of gaussian ), the meaning of laplacian of gaussian in human vision, edge detection and neurophysiology. with different template to different size of target, the small target can be separated from the background by this small infrared target detection method

    從marr演算法的理論基礎? ?高斯平滑濾波器與拉普拉斯運算元的相關知識以及Ｍ ａ ｒ ｒ的計算視覺理論基礎開始，進行了2g （ laplacianofgaussian ，高斯?拉普拉斯）濾波器、 log （ laplacianofgaussian ，高斯?拉普拉斯）模板以及2g濾波器在人類視覺、邊緣檢測、邊緣處理的物理意義以及神經生理學意義方面的分析討論，提出了易於fpga （ fieldprogrammablegatearray ，現場可編程門陣列）實現的基於marr計算視覺的紅外圖像小目標檢測方法。
  17. Specifies the percentage of training cases used to calculate the holdout error, which is used as part of the stopping criteria during neural network learning

    指定用於計算?效組錯誤的培訓案例之百分比，以在類神經網路學習期間作為停止準則的一部分。
  18. A kind of resolution principle based on neural network in the procession of the resolution, computationally hard problem may happen. because neural network has the advantage of learning and parallel algorithmic, we can use it to solve the problem

    基於神經網路的歸結原理實現在數字系統n中，歸結過程會產生大量的計算，自然地，我們會想到利用神經網路學習和并行計算的優點解決這一問題。
  19. From the beginning of the middle of the 1980 " s, the investigation of neural networks has become popular again in us, japan and western europe, in some aspects, such as modules of neural networks, learning algorithm, realization and practice of neural computer, etc, many achievements were obtained. about 100 kinds of modules of networks were put forward

    從80年代中期開始，神經網路的研究在美國、日本、西歐等國家再度掀起熱潮，在神經網路模型、學習演算法、神經計算機實現和應用等方面，取得了令人鼓舞的眾多成果，出現了近百種網路模型，新的演算法及其改進演算法更是層出不窮，使計算機具有更多的智能。
  20. Included are sessions on anatomical, ablation, neurophysiological, and computer modeling techniques, and ways these techniques are used to study brain function

    包括許多堂有關解剖、摘除、神經生理學、和運用計算機模擬的技巧，以及如何利用這些技巧研究腦部功能。
分享友人
分享到 Line

分享到臉書