例句與造句

1. In the method , we have discussed the pretreatment of financial indexes , the choice of the number of hidden - unit , the initial weight and so on , and got a 17 11 5 topology structure . the results have proved that this method is more effective than usual financial analysis . 3
   研究了財務指標的預處理問題、網(wǎng)絡隱含層神經(jīng)元數(shù)選取問題、網(wǎng)絡連接權值的初值選取問題等，給出了17 11 5的網(wǎng)絡拓撲結構，結果表明這種方法進行財務分析比常規(guī)方法有效，提高系統(tǒng)的應用效果。
2. 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(jīng)網(wǎng)絡,將遺傳算法優(yōu)化好的初始權值和閾值作為bp網(wǎng)絡的權值和閾值,采用學習率可變的動量bp算法對神經(jīng)網(wǎng)絡進行了訓練,達到了誤差目標要求,從而實現(xiàn)了bp算法修正網(wǎng)絡權重的目的。
3. After the ls - cma captures a cm signal , the relationship between the weight vector and the do a of the other signals is derived . initial weight vectors are set hi the directions of the other cm signals by lcmv algorithm . thereafter , the blind beamforming for the other cm signals can also be realized
   首先，我們導出了恒模算法收斂于任意一個恒模信號后，其恒模算法的權向量與其它用戶波達角之間的關系，然后在不同用戶的波達方向上形成初始增益，進而對所有的用戶實現(xiàn)波束形成。
4. The fuzzy hyperbolic model , a new approach for modeling of nonlinear system , is subsequently discussed for its validity . based on selecting the initial weights of neural network according to the priority of each input , the parameters can be identified by using bp neural network , which is good for reducing the randomness of initial weights and computing time . by combining self - study ability of neural network with knowledge - expression of fuzzy set theory , fuzzy neural network with self - correction of membership function is lastly constructed to make the approximation of some nonlinear functions
   同其它神經(jīng)網(wǎng)絡模型相比此模型權系數(shù)的初始值可以根據(jù)各個輸入變量在模型辯識中的重要性進行選擇，減少了初始權值設定的隨機性，從而縮短了模型辯識時間最后利用神經(jīng)網(wǎng)絡所具有的自學習能力結合模糊控制較強的知識表達能力，構造具有自動調(diào)整模糊隸屬度函數(shù)的模糊神經(jīng)網(wǎng)絡，并利用它實現(xiàn)非線性函數(shù)的逼近。
5. For further study to improve performance , an adaptive control algorithm based on neural network is tried in stabilization control . a new method of selecting the initial weights of neural network is put forward , which is that the coefficients of discrete equivalent of continuous transfer function in traditional control are used as the initial weights of neural network . adaptive neural network control is combined with traditional control by using different method in different segment
   作為進一步提高穩(wěn)定系統(tǒng)性能的探討，對基于神經(jīng)網(wǎng)絡的參數(shù)自適應調(diào)整控制方法在穩(wěn)定控制中的應用進行了研究，提出了將傳統(tǒng)校正方法經(jīng)離散化后所得到的數(shù)字控制算法的系數(shù)作為神經(jīng)網(wǎng)絡權值初值的新方法，并采用分段控制，將傳統(tǒng)校正方法和神經(jīng)網(wǎng)絡控制方法相結合，取得了較好的控制效果。
6. It's difficult to find initial weight in a sentence. 用initial weight造句挺難的
更多例句：  上一頁