最小極大偏差 的英文怎麼說

中文拼音 [zuìxiǎojídàpiānchā]
最小極大偏差 英文
least-maximum deviation
  • 最 : 副詞（表示某種屬性超過所有同類的人或事物） most; best; worst; first; very; least; above all; -est
  • 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...
  • 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...
  • 偏 : Ⅰ形容詞1 （不正; 歪斜） inclined to one side; slanting; leaning 2 （只側重一面） partial; prejudi...
  • 差 : 差Ⅰ名詞1 （不相同; 不相合） difference; dissimilarity 2 （差錯） mistake 3 [數學] （差數） differ...
  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. The best approximations algorithm is just the method which can solve the mini - max solution of the least value of frequency deviation. because of the reason above, in this paper the best approximations algorithm is introduced into calculating the parameters of atcxo compensation network for the first time

    最佳一致逼近演算法正是能夠求解出使頻率偏差的絕對值最小的極小極大解的一種方法，為此將最佳一致逼近演算法首次應用於模擬溫補晶振補償網路參數的計算中。
  3. A batch least - squares maximum likelihood estimator is employed to calibrate the model coefficients of accelerometer and a polynomial post - fit method is used to establish temperature models of these coefficients. the temperature models of accelerometer bias and scale factor of accelerometer are established between - 20oc and 50 oc. after compensating the temperature error by using these models, the post - fit residuals of the accelerometer output have been improved to 10 ? 5 g, and the trend term of accelerometer changing with temperature basically vanished

    採用最小二乘極大似然估計和多項式擬合的方法，分析加速度計靜態模型系數隨加速度計殼體溫度變化的規律，建立了- 20oc 50oc之間加速度計零偏和標度因數誤差的溫度模型，應用該模型對加速度計溫度干擾進行補償，補償后，加速度計輸出的擬合均方根誤差一到二個數量級，並且基本上消除了加速度計輸出隨溫度變化的趨勢項，使得加速度計測量精度得到了明顯提高。
  4. Automatic limit testing, math scale and offset, statistics minimum, maximum, mean, standard deviation

    自動極限測試，數學運算定標，偏置，統計最小，最大，平均，標準偏差
  5. 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。
  6. In this paper, we discussed the procedures of quantiles, maximum - likelihood, probability weighted moments, moments, least square, the best linear unbiased estimate, good linear unbiased estimation, and the best invariant estimate to the parameters of gumbel distribution, then give out the expectation and variance - covariance respectively. we compared the statistical behavior of these eight estimate procedures not only theoretically but also in the monte - carlo simulation

    本文利用分位數法、極大似然法、概率加權矩法、矩法、最小二乘法、最佳線性無偏估計法、簡單線性無偏估計法、最好線性同變估計法對gumbel分佈中的參數進行估計，分別給出了這八種估計量的期望、方差和協方差。
分享友人
分享到 Line

分享到臉書