極小點 的英文怎麼說

中文拼音 [jíxiǎodiǎn]
極小點 英文
minimal point
  • 極 : i 名詞1 （頂點; 盡頭） the utmost point; extreme 2 （地球的南北兩端; 磁體的兩端; 電源或電器上電流...
  • 小 : Ⅰ形容詞1 （體積、面積、數量、強度等不大） small; little; petty; minor 2 （年紀小的; 年幼的） youn...
  • 點 : Ⅰ名詞1 （液體的小滴） drop （of liquid） 2 （細小的痕跡） spot; dot; speck 3 （漢字的筆畫「、」）...
  1. The traditional neural networks, bp networks, are subject to three hardly conquerable drawbacks in network training and network design a long time, including slow training speed, the training tending to sinking into local minimum and the trained networks having poor generalization capability

    傳統的神經網路（ bp網路）在網路訓練和網路設計上長期受困於三個難以克服的缺陷，即網路訓練速度慢、訓練易陷入局部極小點和網路學習的推廣性能差。
  2. This article puts forward a solution named divide - assemble by deducing the size of bp neural network to overcome entering the local best point, the dividing process is that a big bp neural network is divided into several small bp neural networks, every small bp neural network can study alone, after all small bp neural networks finish their study, we can assemble all these small bp neural networks into the quondam big bp neural networks ; on the basis of divide - assemble solution, this article discusses the preprocessing of input species and how to deduce the size of bp neural network further to make it easy to overcome entering the local best point ; for the study of every small bp neural network, this article adopts a solution named gdr - ga algorithm, which includes two algorithms. gdr ? a algorithm makes the merits of the two algorithms makeup each other to increase searching speed. finally, this article discusses the processing of atm band - width distribution dynamically

    本文從bp網的結構出發，以減小bp神經網路的規模為手段來克服陷入局部極小點，提出了bp神經網路的拆分組裝方法，即將一個大的bp網有機地拆分為幾個小的子bp網，每個子網的權值單獨訓練，訓練好以後，再將每個子網的單元和權值有機地組裝成原先的bp網，從理論和實驗上證明了該方法在解決局部極小值這一問題時是有效的；在拆分組裝方法基礎上，本文詳細闡述了輸入樣本的預處理過程，更進一步地減小了bp網路的規模，使子網的學習更加容易了；對于子網的學習，本文採用了最速梯度? ?遺傳混合演算法（即gdr ? ? ga演算法） ，使gdr演算法和ga演算法的優點互為補充，提高了收斂速度；最後本文闡述了用以上方法進行atm帶寬動態分配的過程。
  3. The process is called coarse - to - fine. in the traditional pyramid method, the template is used and unvaried. but in contact - match algorithm the template is varying, which leads to void dropping into local minimal location

    與傳統匹配方式不同，傳統匹配方式中匹配模板一般不變化，而接觸匹配演算法中的模板在比較過程中不斷變化，並且有避免落入局部極小點的優點。
  4. An indirect self - adaptive fuzzy - neural network controller ( fnnc ) has been proposed with its parameters and the structure tuned simultaneously by ga in virtue of the powerful optimization property of ga. the structure of the controller is based on the radical basis function ( rbf ) neural network with gaussian membership functions. the performance of the proposed fnnc is compared with a conventional fuzzy - pid controller and the simulation results show that the fnnc presents encouraging advantages

    針對神經網路採用一維反向傳播訓練演算法速度較慢且易於陷入局部極小點的不足，設計了一種間接自校正模糊神經網路控制系統，利用遺傳演算法（ ca ）對隸屬度函數的結構和參數進行優化，模擬比較表明該控制比模糊pid控制具有更優的性能。
  5. Two convergence theorems, which show that under suitable conditions evolution strategy asymptotically converges to a global minimum point with probability one, are given

    對于有界閉集上的連續函數，證明了進化策略以概率為1收斂（幾乎處處收斂）于優化問題的全局極小點。
  6. A stationary point which is neither a local maximum nor a local minimum point is called a saddle point.

    一個既不是局部極大點又不是局部極小點的平穩點稱為一個鞍點。
  7. In the chapter of character segmentation, the traditional method of finding minimum vertical projections combined with plate license format is used. the use of space mark matching method proposed in this dissertation to ensure the first segmentation position obtains a very high rate of success

    在字元分割方面，提出了間隔符區域匹配的方法獲得分割起始位置、並以二值圖像垂直投影尋找極小點結合車牌制式先驗知識的演算法，以消除車牌左右兩端定位精度對字元分割的影響。
  8. In the first part of this thesis, to cope with the low searching efficiency and premature of simple genetic algorithm ( sga ), a kind of improved genetic algorithm ( iga ) is presented

    本文首先針對簡單遺傳演算法（ sga ）中存在的收斂速度慢、易陷入局部極小點（即早熟）等缺點，對其進行了改進。
  9. Based on the theory of reyleigh minimum, the minimum of energy function of neural network was mapped to the eigenvector that was mapped to the minimal eigenvalue of the generalized eigenvalue problem, by which the precise solution of minimal eigenvalue was gained while the neural network moving to the minimum of energy function

    本文應用reyleigh極小值原理，將神經網路的能量函數的極小點對應于廣義特徵值問題的極小特徵值所對應的特徵向量，在神經網路向著能量函數極小點運動的同時得到了極小特徵向量的精確解答。
  10. In unconstrained optimization, we deal with the standard problem of finding the minimum of a function f : rn - r. if we assume that the function is twice continuously differentiable, many methods can be applied to find the minimum

    在無約束最優化中，考慮尋找f ： r ~ n r的極小點。假設f是二次連續可微的，可以有許多方法尋找它的極小點。
  11. The neural network has been studied for about many years and won successes in many fields, including pattern recognition, data mining and so on. unfortunately, many problems, such as local minimum, overtraining, generalization and so on, are encountered in the theories, design and applications

    神經網路在模式識別、函數逼近、數據挖掘等許多領域已經取得了很多成功，但目前神經網路的理論和應用都還存在一些困難，如局部極小點、過學習、欠學習以及推廣能力等問題。
  12. 7. for the purpose of analyzing its asymptotic convergence properties the evolution strategy procedures for real - valued function optimization are described. two convergence theorems, which show that under suitable conditions the evolution strategy asymptotically converges to a global minimum point with probability one, are given

    對于有界閉集上的連續函數，利用作者給出的一種簡潔的方法，證明了一類進化策略以概率為1收斂（幾乎處處收斂）于優化問題的全局極小點，為進化演算法的收斂性分析提供了一種新的模式。
  13. Using error back propagation algorithm. the limitation of the bp net is also improved ; 2 > when prediction with little training sample set and large variable size is concemed, this paper abstracts the prime factors from the training sample set using rough set theory, then only inputs the prime factors into ann. this diminishes the size and the input nodes number of ann

    對于即網路本身易陷入局部極小點及收斂速度慢的問題，在文中也得到了改進； 2 、對于財政轉移支付中標準收入的測算屬于多指標小樣本的預測問題，文中首次利用粗集理論對初始的指標體系進行約簡，提取出關鍵性的因素作為神經網路的輸入。
  14. A chaos search for implementing optimal multi - user detection in cdma system has been proposed. computer simulation illustrated that this way has many powerful abilities. its capability is better than the traditional detection and the multi - series detection, it is near to the omd which was presented by verdu, and then its beginning condition is insensitivity, near - far insensitivity, eliminate interference, it can converge to global minimum point and hold down the noise interference

    通過模擬證明：其性能優于傳統檢測器（ cd ） 、多級多用戶檢測器（ msd ）而接近於文獻[ 1 ]中提出的最佳多用戶檢測器（ omd ） ，具有對初始條件不敏感、對「遠近」問題不敏感和優良的抗干擾性能，並提高了通信系統的系統容量，能尋優到全局極小點，以及能抑制噪聲干擾，而且，計算復雜度較低。
  15. ( 6 ) by the research of clustering capability of som, associated with fuzzy clustering analysis, we can realize the diagnosis of multiple faults of turbine generator - set. ( 7 ) by the analysis of the fuzzy - c partition and the genetic algorithm, a new method combing with them is put forward. this method can prevent the fuzzy - c partition from the local least point and can diagnose the steam turbine generator - set ' s multiple faults more effectively

    （ 7 ）通過模糊c -劃分極易陷入局部極小值和遺傳演算法有全局尋優特點的分析，提出了將兩者相結合的聚類分析新方法，不僅可克服模糊c -劃分陷入局部極小點的缺陷，而且能對汽輪發電機組的多故障進行有效的診斷。
  16. The several ones that have more lager sensitivity to embankment settlement are found out. then, aimed at the traditional three - layer bp network ' s shortages : easily getting into local minimum value and slow convergence, the modification combined momentum method with self - adaptation study velocity is made, and one improved bp network is put forward. finally, according to the results from above sensitivity analyses, the nonlinear model main parameters of each natural layer in roadbed are approximately rectified using the improved bp network technology founded on its stronger nonlinear mapping capacity and the settlement measurements

    採用非線性有限元程序，對鄧肯-張模型中8個參數與路堤沉降的關系進行了詳細分析，找到了影響沉降的主要參數；接著，針對傳統的三層bp網路具有收斂速度慢、易陷入局部極小點等不足，對其進行了修正，提出了改進的bp神經網路模型；最後，根據上述靈敏度分析結果，基於改進的bp網路模型較強的非線性映射能力和前期沉降實測資料，對路基中各天然土層的非線性模型主要參數進行了反分析修正； （ 4 ）路堤沉降計算一維法中考慮應力歷史、側向變形的研究。
  17. The icm method is the fastest one, which is equivalent to the zero temperature annealing procedure, but it will drop into the local minima inevitably in the segmentation task

    Icm方法是最為快速的退火方法，它相當于把溫度固定在0度時的退火過程，但不可避免地會收斂於一個局部極小點。
  18. The statistical learning theory and support vector machine have been introduced. the model selection, over - learning, nonlinear, dimensions curse and local minimum problems have been researched

    介紹了統計學習理論和支持向量機方法，研究分析了機器學習方法中存在的模型選擇、過學習、非線性、維數災難和局部極小點等問題。
  19. A new genetic neural network is to conduc the non - rigid modeling, which is first put forward, in accordance with some drawbacks of the current software compensation, which include low accuracy and trouble some expressions. and the current difficult questions, which include local minimum problem and the selection of the number of neural network hidden units, are done

    針對現有誤差補償過程中精度較低等問題，提出了一種改進的遺傳神經網路演算法建立三坐標測量機非剛性誤差模型，這種演算法克服了現有bp演算法神經網路建模存在的局部極小點、網路隱單元數選擇等問題。
  20. This method can approach local extreme value available, but it is not the optimal solution or optimal resolution

    用這種方法可以有效逼近解的局部極小點，但不一定能得到最佳解或最佳的解析度。
分享友人
分享到 Line

分享到臉書