例句與造句

1. Back propagation algorithm
   反傳算法
2. Design of on - line learning based error back propagation algorithm in simulation servo system
   基于在線學(xué)習(xí)誤差反傳算法的仿真伺服系統(tǒng)設(shè)計(jì)
3. The multilayer perception , trained by the back propagation algorithm , is currently the most widely used neural network
   Bp神經(jīng)網(wǎng)絡(luò)是目前神經(jīng)網(wǎng)絡(luò)理論發(fā)展最完善、應(yīng)用最為廣泛的網(wǎng)絡(luò)。
4. Chapter four details the basis of the modeling of the thesis - - error back propagation algorithm , or bp , which is the stress of the thesis
   2005年4月末,金融機(jī)構(gòu)個(gè)人貸款余額達(dá)到27043億元,比上年同期增長(zhǎng)了57 % ,呈現(xiàn)了快速發(fā)展的態(tài)勢(shì)。
5. The algorithm give over vice of the simple back propagation algorithm ( sbp ) that plunge the part extremes in some intricate nonlinear problems
   同時(shí)，針對(duì)sbp神經(jīng)網(wǎng)絡(luò)對(duì)于復(fù)雜的非線性問(wèn)題容易陷入局部極值，提出了改進(jìn)的bp算法( nfcs - caf ) 。
6. It's difficult to find back propagation algorithm in a sentence. 用back propagation algorithm造句挺難的
7. Chapter 4 presents an error back propagation algorithm with quadratic momentum of the multilayer forward neural networks that will speed up the error convergence velocity
   本文提出一種帶二次動(dòng)量項(xiàng)的多層前向網(wǎng)絡(luò)誤差反傳算法，提高了神經(jīng)網(wǎng)絡(luò)的誤差收斂速度。
8. In this model , back propagation algorithm based on forward networks was conducted to learn information of historical data and to train the network weights
   以人工神經(jīng)網(wǎng)絡(luò)的前饋型網(wǎng)絡(luò)為基礎(chǔ)結(jié)構(gòu)，基于反向傳播算法進(jìn)行學(xué)習(xí)和訓(xùn)練來(lái)擬和證券價(jià)格指數(shù)的運(yùn)動(dòng)趨勢(shì)。
9. Feedforward networks use back propagation algorithm to train a multi - layer network . after training , the multi - layer network can fit the function in the data space very well
   前向網(wǎng)絡(luò)利用反向傳播算法訓(xùn)練多層網(wǎng)絡(luò)，使訓(xùn)練后的網(wǎng)絡(luò)較好地?cái)M合樣本空間中各點(diǎn)的函數(shù)值。
10. The artificial neural networks ( ann ) with back propagation algorithms coupled with the sequential pseudo - uniform design ( spud ) was applied and demonstrated successfully to the modeling of the pmr system using limited but adequate experimental data
    我們采用接續(xù)式擬均勻設(shè)計(jì)來(lái)安排實(shí)驗(yàn)取得少量但充足的數(shù)據(jù)并以類神經(jīng)網(wǎng)路來(lái)建構(gòu)鈀膜反應(yīng)器之代表性模式。
11. In the stage of training , nntcs applies labeled documents to ann for training , and the error back propagation algorithm ( bp ) is employed to adjust weights of the networks . after training , the final fixed weights are saved as knowledge of classification
    在文本訓(xùn)練的時(shí)候，利用標(biāo)記好的訓(xùn)練文檔集進(jìn)行網(wǎng)絡(luò)訓(xùn)練，誤差反饋算法對(duì)網(wǎng)絡(luò)進(jìn)行權(quán)值調(diào)整，得到固定的權(quán)值作為分類知識(shí)存儲(chǔ)。
12. In this paper , we improve the objective function of back propagation algorithm based on different financial actual situation . change the objective function into the expectation and the variance of error function to make its application more wide
    本文首先基于bp算法應(yīng)用于金融實(shí)務(wù)領(lǐng)域的不同，對(duì)原bp算法的單一目標(biāo)函數(shù)進(jìn)行了改進(jìn)，分別取其期望目標(biāo)和方差目標(biāo)，進(jìn)行了bp算法的推廣，使其應(yīng)用范圍更廣。
13. In order to override the well - known limitation of back propagation algorithm , such as local grade problem , we suggest genetic algorithm , a global optimization algorithm , to optimize the weights set . the different parts of this model were modularized and combined as a prediction system
    通過(guò)對(duì)固定網(wǎng)絡(luò)結(jié)構(gòu)的權(quán)系值進(jìn)行遺傳操作，優(yōu)化網(wǎng)絡(luò)的權(quán)系值組合，快速收斂到最優(yōu)權(quán)系值組合，進(jìn)而提高網(wǎng)絡(luò)的分析預(yù)測(cè)效率和能力。
14. The multiplayer forward neural network and its training algorithm are thorough analyzed , error back propagation algorithm is derived from the mathematic , the problem of bp algorithm is indicated . the improved bp algorithm with many target recognition is constructed
    詳細(xì)分析了多層前饋型神經(jīng)網(wǎng)絡(luò)描述及訓(xùn)練算法機(jī)理，從數(shù)學(xué)的角度推導(dǎo)了誤差逆?zhèn)鞑ニ惴? bp算法) ，同時(shí)指出了bp算法存在的問(wèn)題。構(gòu)建了一種用于多目標(biāo)識(shí)別的改進(jìn)的bp算法。
15. On the basis of analysing multilayer forward artificial neural networks which based on back propagation algorithms and basic principles of the adaptive noise cancellation system , this paper sets up an adaptive noise cancellation controller based on artificial neural network , which is proved to be more efficient in the noise cancellation and has robust performance based on simulink of matlab at the end , this paper proposes some advices of model and algorithms
    在對(duì)基于誤差反向傳播學(xué)習(xí)算法的多層前向人工神經(jīng)網(wǎng)絡(luò)進(jìn)行分析基礎(chǔ)上，結(jié)合傳統(tǒng)自適應(yīng)噪聲抵消系統(tǒng)基本原理，建立了基于人工神經(jīng)網(wǎng)絡(luò)的自適應(yīng)噪聲抵消器，經(jīng)基于matlab的simulink仿真實(shí)例證明，具有很強(qiáng)的噪聲濾除能力和魯棒性。最后并提出了網(wǎng)絡(luò)及算法進(jìn)一步改進(jìn)的方法。
16. Based upon the deficiencies of the back propagation algorithm in the practical application , after some mechanisms effecting the network training and the other performances are analyzed when training samples with disturbance are employed in training , in this paper , through combining the chief thoughts of the classical bp algorithm and the robust statistic technique , improving the optimal algorithm of the bp algorithm , a new algorithm with high robustness - robust adaptive bp algorithm is proposed , and also make a good effect when integrated this new algorithm with the dynamical bp network to predict the stock price
    本文從基本bp算法在應(yīng)用中存在的不足出發(fā)，著重分析了訓(xùn)練樣本中所含噪聲對(duì)基本bp算法在網(wǎng)絡(luò)訓(xùn)練過(guò)程中產(chǎn)生的不良影響，并以此為依據(jù)，采用魯棒統(tǒng)計(jì)技術(shù)，同時(shí)在優(yōu)化算法上做了一些有益的改進(jìn)，提出一種新的具有較強(qiáng)抗干擾能力的bp算法? ?魯棒自適應(yīng)bp算法，并將其應(yīng)用于動(dòng)態(tài)bp網(wǎng)絡(luò)，進(jìn)行股票價(jià)格的預(yù)測(cè)，取得了較好的預(yù)測(cè)效果。
更多例句：  下一頁(yè)