練習誤差 的英文怎麼說

中文拼音 [liànxíwùchā]
練習誤差 英文
practice error
  • 練 : Ⅰ名詞1 （白絹） white silk 2 （姓氏） a surname Ⅱ動詞1 （加工處理生絲） treat soften and whiten s...
  • 誤 : Ⅰ名詞（錯誤） mistake; error Ⅱ動詞1 （弄錯） mistake; misunderstand 2 （耽誤） miss 3 （使受損害...
  • 差 : 差Ⅰ名詞1 （不相同; 不相合） difference; dissimilarity 2 （差錯） mistake 3 [數學] （差數） differ...
  • 練習 : 1. （反復學習） practise; practice 2. （習題或作業等） exercise
  • 誤差 : error
  1. Compared with the classical bp algorithm, robust adaptive bp algorithm possesses some advantages as following : ( 1 ) increasing the accuracy of the network training by means of using both the relative and absolute residual to adjust the weight values ; ( 2 ) improve the robustness and the network convergence rate through combining with the robust statistic technique by way of judging the values of the samples " relative residual to establish the energy function so that can suppress the effect on network training because of the samples with high noise disturbances ; ( 3 ) prevent entrapping into the local minima area and obtain the global optimal result owing to setting the learning rate to be the function of the errors and the error gradients when network is trained. the learning rate of the weights update change with the error values of the network adaptively so that can easily get rid of the disadvantage of the classical bp algorithm that is liable to entrap into the local minima areas

    與基本bp演算法相比，本文提出的魯棒自適應bp演算法具有以下優點： （ 1 ）與魯棒統計技術相結合，通過訓練樣本相對偏差的大小，確定不同訓練樣本對能量函數的貢獻，來抑制含高噪聲干擾樣本對網路訓練的不良影響，從而增強訓練的魯棒性，提高網路訓練的收斂速度； （ 2 ）採用相對偏差和絕對偏差兩種偏差形式對權值進行調整，提高了網路的訓練精度； （ 3 ）在採用梯度下降演算法對權值進行調整的基礎上，通過將學習速率設為訓練誤差及誤差梯度的特殊函數，使學習速率依賴于網路訓練時誤差瞬時的變化而自適應的改變，從而可以克服基本bp演算法容易陷入局部極小區域的弊端，使訓練過程能夠很快的「跳出」局部極小區域而達到全局最優。
  2. In this method, ga is used to optimize connection weights of forward - back neural network until the learning error has tended to stability, then we use sp algorithm with optimized weights to finish short - term load forecasting process

    我們用遺傳演算法來訓練網路參數，直到誤差趨於一穩定值，然後用優化的權值進行bp演算法，實現短期負荷預測，模擬實驗結果表明該方法加快網路學習速度，並能提高負荷預測精度。
  3. Taking the evaluation criterion of lake nutrient states as sample pattern, the network was trained in the light of learning rule of error back propagation network

    將湖泊營養狀態評價標準作為樣本模式提供給網路，按照誤差逆傳播網路的學習規則對網路進行訓練，經過39925次學習后，網路達到預先給定的收斂標準。
  4. The causes consist of the following : the ambiguity of the grammatical functions of words, negative transfer of mother language ; false analogy of the target language rules ; negative transfer of drilling and learning strategies ; negligence of cultural difference

    造成搭配錯誤的原因主要在於對詞的語法功能沒有清楚的理解、來自於母語的干擾、對目的語規則的泛化運用、習得過程中的訓練遷移和學習策略、忽略中英文化差異。
  5. Realization of improved bp algorithm - single output three layers " artificial neural network generator base on improved bp algorithm has been developed by the author, and the generator has some functions that the number of neuron in first and second layer and theirs related training parameters such as learning rate. momentum factor a and the value of sum error e can all be self - defined by the users ; connection weights and threshold in each layer ' s neuron training data and teaching signals can also be input or modified in the friendly interface

    生成器功能是:網路結構中的第一、二層神經元個數和訓練參數中的學習速率粉，動量因子a和期望誤差值:可由用戶在一定范圍內自定義;各層的權值、閥值、網路初始樣本值及教師值可在友好的界面下輸入、修改。
  6. I improve the back propagation arithmetic, and apply fuzzy entropy to the training and studying of nerve network, a new arithmetic based on fuzzy entropy and error is presented

    對現有的bp演算法進行了改進，將模糊熵用於神經網路的訓練和學習，提出一種基於模糊熵準則和誤差平方和準則的多準則模式識別方法。
  7. The diagnosis program is made in visual c + +. the samples are trained with this network, during which the relationships between the network parameters ( such as rule number, study rate, expert network initial error and gate network error, circulation times and power index ) and learning error were probed into, and the outcome can provide the basis for network parameter selecting

    並採用visualc + +編制了系統程序，首先通過分層混合專家網路對故障樣本進行訓練，在訓練中對分層混合專家網路各參數（規則數、學習率、門網路中止誤差、專家網路初試迭代誤差、循環次數、加權指數等）與學習誤差平方和的關系進行了探討，其結果為樣本網路參數的合理選取提供了依據。
  8. In this paper, overall design philosophy and measure while diagonose the prefabricated substation using ann theory are defined, including the definition of fuzzy expression method for fault symptoms, the definition of typical fault collection and typical fault sign collection, the definition of the format of the learning sample and test sample, and the definition of fault diagnosis model formed in coordination by multi ann whose diagnosis principle are also described. a practical software using visual c + + 6. 0 and access2000 as developing instrument are developed on the basis of diagnosis principle put forward by this paper

    本文確定了應用神經網路理論對箱式變電站進行故障診斷的總體設計思想和步驟：確定了監測數據的預處理模糊化方法；建立了箱式變電站典型故障集和典型故障徵兆集；確定了學習樣本的格式，完成了學習樣本的生成；確定了神經網路結構和參數，並對學習樣本應用本文的學習演算法進行了學習訓練，使誤差控制在給定范圍內；以集散監測診斷系統的思想，提出了由多個神經網路協同構成的多神經網路故障診斷模型，並論述了其診斷原理。
  9. This paper ' s study was emphasized on : 1. set up bp neural network set up bp network by matlab toolbox. chosen transfer function among every layer, training error and learning rate were included

    重點研究內容： （ 1 ）建立bp （ backpropagation ）神經網路用matlab提供的人工神經網路工具箱建立網路，包括選擇各層間的傳遞函數、確定網路訓練誤差和學習速率等，為建立定價模型做準備。
  10. As for a certain value of the training error, if the predicted value of a neural network model lies in true value confident interval, it is believed that the true value of a neural network output variable be obtained, and the training process of a neural network is over

    該方法由實測值求出相應的真值置信區間，若訓練誤差的取值使得網路預測值落在真值置信區間內就可以認為此時的訓練學習反映了網路輸出變量的真值情況，學習就可以結束。
  11. The main conclusions are as follows : through the different structure and algorithm application of bp model in the predication of regional groundwater hydrology, the hidden layers number, learning rates, neuron number of hidden layer and training errors of bp model and accelerated bp algorithm which influence the convergence effects and test results of model are compared each other. some application technology related parameters of bp structure design are put forward

    論文取得了以下主要成果：通過不同bp網路結構和演算法在區域地下水文預測中的實例研究，重點比較了不同層次結構、隱層單元數、學習速率、訓練收斂誤差等4個基本要素及不同演算法、不同樣本容量等對模型收斂效果、模擬、檢驗與預報結果的具體影響。
  12. In training of back - propagation neural network, parameter adaptable method which can automatically adjust learning rate and inertia factor is employed in order to avoiding systemic error immersed in a local minimum and accelerating the network ' s convergence ; introduced the further optimization of the network ' s structure, it gives the research result of selection of the hidden layers, neurons, and the strategy of re - learning, compared the sums of the deviation square of this algorithm with conventional bp algorithm, as a result, the approach accuracy and the generalization ability of the network were extremely improved

    在對前饋神經網路的訓練中，使用參數自適應方法實現了學習率、慣性因子的自我調節，以避免系統誤差陷入局部最小，加快網路的收斂速度；提出了優化bp網路結構的實驗研究方法，並給出了有關隱含層數和節點數選擇以及再學習策略引進的研究結果。將該演算法同傳統bp演算法的預測偏差平方和進行比較，結果證實網路的逼近精度及泛化能力均得到了極大的提高和改善。
  13. Radial basis function neural network ( rbfnn ) is chosen to build predictive model. rbfnn is a special type of neural network linear - in - weight in nature and having nonlinear processing properties. finally, an adaptive filter is applicable to do the followed weak signal extraction work

    接著選用徑向基函數神經網路（ radialbasisneuralnetwork ， rbfnn ）建立混沌時間序列預測模型，徑向基函數神經網路是一種局部逼近的人工神經網路，訓練簡潔而且學習收斂速度快，能夠逼近任意非線性函數，最後將預測誤差送入自適應信號分離器進行處理，檢測出微弱信號。
  14. Because the weight space formed by the bp neural network ' s global error function, which include extreme point, is a hyper - surface, considering the initial parameters of bp neural network ' s structure, so the bp neural network has a inherent deficiency of easily falling into local minimum

    由於bp神經網路的全局誤差函數構成的權值空間是包含多個極值點的超曲面，加之即網路訓練開始網路結構參數是隨機給定的，因而bp神經網路在學習訓練中容易陷入局部極小。
  15. This thesis expounds fundamental principle and realization technique of artificial neural network and genetic algorithm, and redacts artificial neural network procedures. - ( l ) adopting batch processing high - speed algorithm, the thesis redacts back - propagation network procedure to enchance training velocity, in which learning rate and momentum parameters are modulated self - adaptably during error correction

    本文闡述了人工神經網路和遺傳演算法的基本原理及實現技術，並在此基礎上利用matlab5 . 3編寫了人工神經網路程序： （ 1 ）編寫了bp人工神經網路程序，採用vogl 「批處理」快速演算法，學習速率、動量參數在誤差修正過程中自適應調節，提高了訓練的速度。
  16. Furthermore, because the three grades decelerate control method, which is used widely, in stack crane control in china has some shortcoming, two rbf neuron network applied in position error study and dot position control is put forward. because neuron network is of self - study, emendation and modification can be achieved in control and can remedy the shortcoming caused by shortage of sample

    另外，本文還針對目前國內在對堆垛機控制方面普遍採用的三段式減速控制規律的弊病，提出用兩個rbf神經網路分別作為位置誤差學習器和點位位置控制器，由於神經網路的自學習功能，可以使得在控制當中不斷校正和修改在訓練時由於樣本不足造成的缺憾。
  17. Besides the adaptive adjust of learning rate and momentum factor, this algorithm can give appropriate permitted convergence error with adaptive adjust in the course of learning. so it overcomes the faults of the controlling means used in traditional bp algorithm

    該演算法在學習過程中，除了對學習率和動量因子進行自適應調整外，還能根據網路的實際訓練情況自適應確定允許均方誤差的值，從而克服了傳統的bp演算法在學習過程中採用的控制方法存在的缺陷。
  18. Because neural network is based upon empirical risk minimization and asymptotic theories, it is suitable to deal with situations where the amount of samples is tremendous and even infinite

    神經網路的理論基礎是最小化經驗誤差，這種基於傳統的漸進理論的學習方法，在訓練樣本點無窮多時是適用的。
  19. The back - propagation neural network is self - defined. the optimized weights and bias obtained by ga are used as initial weights and bias of the back - propagation ( bp ) neural network. then, the neural network is trained by the variable study rate momentum of bp algorithm, the error goal is achieved by massive experiments

    自定義了bp神經網路，將遺傳演算法優化好的初始權值和閾值作為bp網路的權值和閾值，採用學習率可變的動量bp演算法對神經網路進行了訓練，達到了誤差目標要求，從而實現了bp演算法修正網路權重的目的。
分享友人
分享到 Line

分享到臉書