nn neural network 中文意思是什麼

nn neural network 解釋
神經網路
  • nn : 第十四集
  • neural : adj. 【解剖學】神經（系統）的；神經中樞的；【解剖學】背的，背側的。adv. -ly
  • network : n. 1. 網眼織物。2. （鐵路、河道等的）網狀系統，網狀組織，廣播網，電視網，廣播[電視]聯播公司。3. 【無線電】網路，電路。4. 【計算機】電腦網路，網。
  1. In the thesis, the general situation of the domestic and abroad developments in the field of the numerical control interpolation algorithm for aspheric surface machining is reviewed firstly, for the poorness of recent numerical control interpolation algorithm, an numerical control interpolation algorithm that based on the genetic algorithm ( ga ) and neural network ( nn ) is introduced

    在數控系統中，它是生成加工軌跡的一個最基本的子程序，在很大程度上決定了數控機床的加工精度和最大進給速度。本文首先綜述了國內外非球曲面超精密加工中所運用的插補演算法的發展概況。
  2. It is very important to estimate the basic parameters in helicopter preliminary design. neural network ( nn ) has the advantages in estimating accuracy and generalization over traditional methods. however, there are some difficulties in using nn, e. g., how to select a proper network structure and the number of hidden layers. in this paper, structure and connection weight of a three - layer nn are optimized by genetic algorithm, and the optimized network is applied to helicopter sizing. the proposed method can not only give an optimal nn structure and connection weight, but also reduce the prediction error and has the capability of self - learning when the latest data are available. furthermore, this method can be easily applied to helicopter design systems

    在直升機初步設計階段估算其基本參數是很重要的.神經網路的通用性和精度比傳統的估算方法有更多的優勢，但是在應用神經網路時存在如何選擇合適的網路結構和隱層節點數目等一些困難.應用遺傳演算法優化三層神經網路結構和連接權重，並將優化得到的網路應用於直升機參數選擇中.該方法不但可以給出一個最優的神經網路結構和連接權重，而且降低了估算誤差，具有及時應用最新數據學習的能力.此外，該方法易於在直升機設計系統中得到應用
  3. On the basis of introducing the theory of fuzzy control ( fc ) and neural network ( nn ) as a whole, this paper presented a new mixed control method, which was called as neural network - fuzzy control. ( nn - fc ). the nn - fc method combined the strong self - study ability of neural network and powerful experience - expressing ability of fuzzy control to meet the need of real - time control

    在系統地介紹智能控制理論中的模糊控制和神經網路控制理論之後，引入了模糊控制和神經網路控制相結合的產物? ?神經模糊控制，將模糊邏輯推理的強大結構性知識表達能力與神經網路的強大自學習能力集於一體，彌補了模糊控制需要系統先驗知識且缺乏自學習功能的不足。
  4. Next, the data are pre - processed to set up the neural network ( nn ) modal. then, the frequency vectors are put into the nn as the input data, however, the damage position and the damage degree are treated as the desired output

    接著，以頻率向量作為神經網路的輸入值，與之相應的損傷位置和損傷程度作為神經網路的期望輸出值，對神經網路進行基於遺傳優化的學習，直至收斂。
  5. Being different from traditional neural network or nn, nn is based on traditional statistics, which provides conclusion only for the situation where sample size is tending to infinity, while svm is based on statistical learning theory or slt, which is a small - sample statistics and concerns mainly the statistic principles when sample are limited, especially the properties of learning procedure

    支持向量機（ svm ）是九十年代中期發展起來的新的機器學習技術，與傳統的神經網路（ nn ）技術不同， svm是以統計學習理論（ slt ）為基礎， nn是以傳統統計學理論為基礎。傳統統計學的前提條件是要有足夠多的樣本，而統計學習理論是著重研究小樣本條件下的統計規律和學習方法的，它為機器學習問題建立了一個很好的理論框架。
  6. Firstly, influence factors of generalization of neural network are presented in this thesis, in order to improve neural network ’ s generalization ability and dynamic knowledge acquirement adaptive ability, a structure auto - adaptive neural network new model based on genetic algorithm is proposed to optimize structure parameter of nn including hidden layer nodes, training epochs, initial weights, and so on ; secondly, through establishing integrating neural network and introducing data fusion technique, the integrality and precision of acquired knowledge is greatly improved. then aiming at the incompleteness and uncertainty problem consisting in the process of knowledge acquirement, knowledge acquirement method based on rough sets is explored to fulfill the rule extraction for intelligent diagnosis expert system, by completing missing value data and eliminating unnecessary attributes, discretization of continuous attribute, reducing redundancy, extracting rules in this thesis. finally, rough sets theory and neural network are combined to form rnn ( rough neural network ) model for acquiring knowledge, in which rough sets theory is employed to carry out some preprocessing and neural network is acted as one role of dynamic knowledge acquirement, and rnn can improve the speed and quality of knowledge acquirement greatly

    本文首先討論了影響神經網路的泛化能力的因素，提出了一種新的結構自適應神經網路學習演算法，在新方法中，採用了遺傳演算法對神經網路的結構參數（隱層節點數、訓練精度、初始權值）進行優化，大大提高了神經網路的泛化能力和知識動態獲取自適應能力;其次，構造集成神經網路，引入數據融合演算法，實現了基於集成神經網路的融合診斷，有效地提高了知識獲取的全面性、完善性及精度;然後，針對知識獲取過程中所存在的不確定性、不完備性等問題，探討了運用粗糙集理論的知識獲取方法，通過缺損數據補齊、連續數據的離散、沖突消除、冗餘信息約簡、知識規則抽取等一系列的演算法實現了智能診斷的知識規則獲取;最後，將粗糙集理論與神經網路相結合，研究了粗糙集-神經網路的知識獲取方法。
  7. The application of bp neural network to speed control system on usm is discussed, and a program is designed for training the bp neural network by matlab ’ s nntool, a three layers neural network of 2 - 8 - 1 is determined through simulation, then write the weights and biases of the nn into dsp to make on - line training, and it reaches the purpose of controlling usm ’ s speed

    利用matlab7 . 0中的神經網路工具箱進行結構設計和離線訓練，通過模擬實驗最終確定了2 - 8 - 1的三層網路結構，將訓練后得到的權值、閾值結果寫到dsp中，進行控制過程中給定速度的在線訓練，從而達到控制電機轉速的目的。
  8. Aiming at the high control performance of the mach number system in nf - 6 wind tunnel, we introduce the self - adapt control strategy based on bp neural network ( nn ), which it use adapt character of nn to control mach number of nf - 6 wind tunnel

    針對nf - 6風洞對馬赫數控制系統提出的高要求，本文採用了一種基於bp神經網路的自適應控制方法，即：用神經網路自適應特性對風洞馬赫數進行控制。
  9. ( 5 ) the nn ( neural network ) prediction model of ground settlement in the shield tunneling is proposed

    （ 5 ）探討和研究了神經網路模型在盾構掘進時引起的地表沉降預測方法及安全性評價。
  10. Intelligent control techniques such as : the control based on neural network ( nn ), fuzzy control etc. are used widely in the control of machine tool, robot, instrument

    智能控制技術主要包括：專家系統、神經網路控制、自適應控制、模糊邏輯控制等，它在機器人、機床控制以及儀器儀表等方面被廣泛的應用。
  11. Okay you ' ll say this is what we can do simply by training some randomly initialised neural network ( nn ) with a supervised or unsupervised algorithm

    好的，你也許會說我們僅要做的就是訓練一些隨機初始化的有或者沒有監督演算法的神經網路. 。
  12. Aim at the neural network get local optimum easily, the speed of convergence is slow, the quantity of training excessive and so on. this paper adopted the ga optimize the nn firstly, and then the nn algorithm

    針對神經網路易出現局部最優點、收斂速度慢和訓練量過大等問題，本文先利用遺傳演算法對神經網路進行優化后，再執行神經網路的演算法步驟。
  13. So it is necessary to apply the neural network ( nn ) and genetic arithmetic ( ga ) to the solving of these equations, it can simplify the diagnosis process and reduce the testing time

    有必要在此基礎上，將神經網路及遺傳演算法方面最新研究成果應用到故障診斷方程的求解，避免復雜的計算和耗時而影響故障診斷的實際應用。
  14. The neural network methology for heat transfer system of underground heat exchanger was also introduced, which lay emphasis on systematics, entirety and fuzzy systematics, and established predication modeling using neural network. from the computer simulation results, it was concluded that with nn modeling the precision was very high. it is worth to developed and applied for engeering practice and different situation

    本文還介紹了主要從系統性、整體性和非線性上來描述地下埋管傳熱系統的神經網路，並針對不同輸入和輸出變量建立了神經網路預測模型，對埋管換熱進行模擬計算和預測，從計算結果可以看出神經網路的模擬值與實驗值相當一致，計算精度高。
  15. Abstract : it is very important to estimate the basic parameters in helicopter preliminary design. neural network ( nn ) has the advantages in estimating accuracy and generalization over traditional methods. however, there are some difficulties in using nn, e. g., how to select a proper network structure and the number of hidden layers. in this paper, structure and connection weight of a three - layer nn are optimized by genetic algorithm, and the optimized network is applied to helicopter sizing. the proposed method can not only give an optimal nn structure and connection weight, but also reduce the prediction error and has the capability of self - learning when the latest data are available. furthermore, this method can be easily applied to helicopter design systems

    文摘:在直升機初步設計階段估算其基本參數是很重要的.神經網路的通用性和精度比傳統的估算方法有更多的優勢，但是在應用神經網路時存在如何選擇合適的網路結構和隱層節點數目等一些困難.應用遺傳演算法優化三層神經網路結構和連接權重，並將優化得到的網路應用於直升機參數選擇中.該方法不但可以給出一個最優的神經網路結構和連接權重，而且降低了估算誤差，具有及時應用最新數據學習的能力.此外，該方法易於在直升機設計系統中得到應用
  16. This paper presents a new model to predict the annual maximum ice - thickness by means of combining levenberg - marquardt neural network ( nn ) with time serial method

    本文將l - m神經網路與時序分析方法相結合提出一種新的模型，用於年極值冰厚預測。
  17. A new speech detection method using the mlp neural network is studied, including the structure of mlp nn and bp learning algorithm

    包括對mlp網路結構和bp學習演算法的介紹，並將該方法應用於不同干擾條件下語音信號的起點檢測。
  18. One of the most advanced algorithm, neural network ( nn ), is discussed for the applying feasibility to the hydraulic loading control system. in chapter 1, the necessity of applying fully automatic control technology in the cctm is synthetically analyzed and discussed

    就當前研究的熱門演算法?神經網路控制演算法應用於試驗機加載控制進行了探討，並應用bp神經網路pid演算法對試驗機簡化模型作了模擬研究，從理論上證明其應用於實際系統的可行性。
  19. In chapter 7, we describe the frame of bp nn ( neural network ) and the algorithm of bp nn ( neural network ) pid control. after applying to the cctm, we can testify the feasibility by comparing the traditional pid control and normal control without pid

    第七章，詳細描述了bp神經網路的具體結構及bp神經網路pid控制的具體演算法實現，得出控制演算法規律，將其應用於試驗機模型，得到此演算法下的控制輸出，並與無pid控制及傳統pid控制進行比較，證明此演算法的可行性。
  20. Through discussions with the fa experts, i present the application of nn ( neural network ) in the process of contending for dealership, that is, to establish b - p three - layer network so to simulate the expert ' s reasoning, and give the suggestions similar to the experts ". in consideration of the transport market ' s changes, the research also provides a forecast of the shipping capacity on several main lines of the world

    通過同貨運代理領域專家的多次探討，本文提出了將神經網路技術應用於「攬取貨源決策」這一重要環節，即建立攬貨決策神經網路，採用b - p三層網路結構，通過對專家所提供的樣本的反復學習，使得系統能模擬貨代領域專家的思維進行推理，給出專家水平的建議。
分享友人
分享到 Line

分享到臉書