例句與造句

1. Fuzzy backpropagation algorithms and their convergence
   模糊反向傳播算法及其收斂性
2. Research on neural network classifier of target based on genetic - backpropagation algorithm
   算法的神經(jīng)網(wǎng)絡目標分類器的研究
3. Application research of backpropagation neutral network in supply chain management performance index
   神經(jīng)網(wǎng)絡在供應鏈管理績效指標評價中的應用研究
4. In order to improve the learning rate of backpropagation neural network , levenberg - marquart algorithm was proposed to learning network optimized weight parameters
   為了提高bp網(wǎng)絡的學習效率，本文將levenberg - marquart ( l - m )算法引入到bp網(wǎng)絡中進行網(wǎng)絡權值的學習。
5. Backpropagation model of the ann is used in knowledge storage and the leverberg - marquardt algorithm based on numerical optimization is used in training the neural networks
   采用了基于數(shù)值優(yōu)化的leverberg - marquardt (簡稱lm )算法，對網(wǎng)絡進行訓練，完成知識庫的組建。
6. It's difficult to find backpropagation in a sentence. 用backpropagation造句挺難的
7. Based on analyzing the multilayer perceptron neural network , it induces the error backpropagation algorithm while taking the hyperboloid tangential function as nonlinear activation function
   在分析多層感知器神經(jīng)網(wǎng)絡的基礎上，推導了雙曲正切函數(shù)為激勵函數(shù)的誤差后向傳播算法。
8. Yu , shang - wu ( 1998 ) , " an application of backpropagation networks on forecasting the stock index futures " , joint international conference on contemporary management and comparative management , kaohsiung
   余尚武，吳嘉欽( 1998 ) , "股價指數(shù)期貨對股票市場波動性之影響" ,第七屆證券暨金融市場理論與實務研討會,中山大學。
9. In the thesis , how to use the backpropagation training functions in the matlab toolbox to train feedforward neural networks to solve specific problems is explained . besides that , how to design the interface between matlab and delphi is presented
   本文在簡要介紹了bp神經(jīng)網(wǎng)絡基本原理及其算法的基礎上，詳細介紹了利用matlab神經(jīng)網(wǎng)絡工具箱進行bp網(wǎng)絡模型建立、訓練、仿真的編程方法。
10. During the work of designing the structure of parallel machine tool , in allusion to the main shortcoming of stewart platform mat its workspace is strait , we decide to design a stewart type parallel machine tool which fulfill the given spherical position workspace and have the best dexterity , genetic algorithm is used in this paper . because the calculation of the fitness function is complex , backpropagation arithmetic is used to approach fitness function . the results show that mis method has good accuracy and computing efficiency
    在并聯(lián)機床的結(jié)構(gòu)設計中，針對并聯(lián)機床的工作空間有限且受刀具姿態(tài)影響大的弱點，提出了以保證非零最小可達章動角球形主工作空間的基礎上，使操作靈敏度暨剛度分布最優(yōu)化的設計目標，優(yōu)化方法的選用了遺傳算法，結(jié)合神經(jīng)網(wǎng)絡技術，該方法取得了很好的結(jié)果。
11. Car tracing cauda is a bad traffic safety accident in speedway . more and more people pay attention to it . in recent years people try to solve car elude tracing cauda in theories and technologies . and building tracing cauda model is the fundation for studing car tracing cauda . after analyzing causation of car tracing cauda , and with the neural network theory , this paper gives backpropagation neural network model for solving it , and disccuses a technic scheme for car tracing cauda prediction system , simulation shows the bp neural network model is acceptable
    高速公路汽車追尾是一種嚴重的交通安全事故，引起了交通科技界的廣泛重視.近幾年來，人們試圖從理論與技術上解決高速公路汽車追尾問題，其中建立追尾的數(shù)學模型是研究追尾現(xiàn)象的基礎.文中在分析了汽車追尾的原因后，基于神經(jīng)網(wǎng)絡理論，建立了追尾的bp網(wǎng)絡模型，并討論了追尾預測系統(tǒng)的技術實現(xiàn)方案
12. The study aims at exploring the impacts of backpropagation nervous network system and multivariate analysis on factors of structuring learning - oriented organization and probes into the executives ' behaviors , organizational culture , organized way to learn as well as the relationship between the establishment of the learning - oriented organization and management performance
    摘要本研究目的在運用倒傳遞類神經(jīng)網(wǎng)路模式和多變量分析之方法以探討主管行? 、組織文化與組織學習方式對于建立學習型組織和經(jīng)營績效間之關系。
13. Nowadays , many classification methods and some prediction technologies have been put forward , such as classification by decision tree induction , bayesian classification , classification by backpropagation , k - nearest neighbor classifiers , linear and nonlinear regression . however , none of them is better than others in all application
    在這一研究方向，目前已提出了多種分類方法（如決策樹歸納分類、貝葉斯分類、神經(jīng)網(wǎng)絡分類和k -最鄰近分類等）和一些預測技術（如線性回歸、非線性回歸等） 。
14. As in nature , the network function is determined largely by connections ( weights ) between elements , so that a particular input leads to a specific target output . the cores of backpropagation neural network are the capacity of parallel computing , distribute saving , self - studying , fault - tolerant and nonlinear function approximating . input vectors and the corresponding target vectors are used to train a network until it can approximate a function , associate input vectors with specific output vectors , or classify input vectors in an appropriate way as defined by you
    人工神經(jīng)網(wǎng)絡是一類模擬人類神經(jīng)系統(tǒng)的結(jié)構(gòu)，他揭示數(shù)據(jù)樣本中蘊含的非線性關系，大量處理單元組成非線性自適應動態(tài)系統(tǒng)，具有良好的自適應性、自組織及很強的學習、聯(lián)想、容錯和抗干擾能力，在不同程度和層次上可模仿大腦的信息處理機理，可靈活方便的對多成因的復雜未知系數(shù)進行建模。
15. The flood and drought in both first stage and second stage of rainy season in fujian province were forecasted by the ways of line regression prediction equation and three kinds of artificial neural network models , the results show : the backpropagation ( bp ) , radial basis function ( rbf ) and elman neural network models are much better than line regression prediction equation in historical sample fittings , independent sample test , actual prediction ability
    ( 3 )運用線性回歸預報方程和三種人工神經(jīng)網(wǎng)絡模型對福建汛期旱澇進行預測的實驗表明： bp 、徑向基( rbf )和elman這三種人工神經(jīng)網(wǎng)絡模型在歷史樣本擬合精度上、獨立樣本檢驗結(jié)果和網(wǎng)絡模型的實際預測能力上都明顯優(yōu)于傳統(tǒng)的線性回歸方法。
16. The relevant neural network of a new learning algorithm - backpropagation with kalman filter is proposed in the context of system identification . the basic idea is that the adjusting weigh value of the neual network is taken as the identification of the parameters for the nonlinear system . so , the kalman filtering technique was applied to modify the weight matrices of neural network
    提出了一種新的訓練前饋神經(jīng)網(wǎng)絡的方法? ?神經(jīng)網(wǎng)絡濾波算法，該算法是基于ekf ( extendedkalmanfilter )的神經(jīng)網(wǎng)絡訓練算法，基本思想是將神經(jīng)網(wǎng)絡的權值訓練看作非線性系統(tǒng)的參數(shù)辨識，并通過ekf來解決此參數(shù)識別問題。