neural networks 中文意思是什麼
-
Abstract : artificial neural networks has been applied to simultaneous determination of fluorene and acenaphthene by ultraviolet spectrophotometry. after compared the results of the synthetic samples obtained from the method above mentioned with those from partial least squares ultraviolet spectrophotometry, it shows that satisfied prediction can be obtained by them
文摘:用人工神經網路-紫外吸光光度法不經分離同時測定芴和苊，並與偏最小二乘-紫外吸光光度法比較.對合成樣品進行分析.結果表明，人工神經網路法同偏最小二乘法一樣能獲得滿意的分析結果 -
Finally, the controller working based on the combination of rbf neural networks and traditional pid control was applied to in aclinic kinetic machinery and lifting machinery of tower crane. the simulation of this controller was made using matlab, and the simulation results showed that the control system has some merits, such as quick response, little overshoot, well anti - jamming capacity, and little steady - state error, etc. both the dynamic property and static characteristic of this controller are better than traditional pid controller, and meet the tower crane
應用matlab對塔機的變幅和起升機構的運動控制進行模擬，模擬結果表明基於rbf神經網路整定pid的控制系統具有響應快、超調小及穩態誤差小等優點，其動、靜態性能優于單一pid控制，從而提高了塔式起重機工作機構的工作性能。 -
Chaotic neural networks based routing algorithm in atm network
路由演算法的研究 -
Fuzzy entropy : axiomatic definition and neural networks model
公理化定義和神經網路模型 -
We discuss the forecast method which based on wavelet neural networks by combining good time and frequency local analysis ability which wavelet analysis possesses with learning ability which neural networks possesses, and bring forward a frondose, banausic algorithm in this dissertation0 also, a essential thinking of combined forecast based on wavelet neural networks is described and a essential trait of combined forecast based on wavelet neural networks is pointed out
結合小波分析所具有的良好的時頻局部化分析能力和神經網路所具有的學習能力，討論了小波神經網路預測方法，並給出了其具體、實用的演算法。文中還描述了基於小波神經網路組合預測的基本思想，指出了利用小波神經網路進行非線性組合預測的特點。 -
Thirdly, resorting to cooperation - competition model of biomathematics, this thesis proposes a new co - evolution model. simulation results are shown to verify its effect and practicabilitv. last, standard methods for optimizing neural netvvorks are easily trapped into local optimization, and unable to adjust the structure of neural networks, thus their application is limited to certain extent
本文主要驗證和設計適應性操作運算元和小生境方法保持群體多樣性的能力，實驗表明兩種方法都能較好地達到目的；利用生物合作競爭模型設計協同演化來動態地改變群體規模，實驗表明該模型是有效的；人工神經網路是得到越來越廣泛應用的學習系統，但是由於學習演算法存在一定的缺陷，如易於陷入局部極值，難以調整網路的結構等，使神經網路的應用受到一定的限制。 -
Face recognition on lle algorithm and bp - based neural networks
神經網路的人臉識別 -
Simple conjugation - gradient bp algorithm for feedforward neural networks
前饋神經網路的一種簡單共軛梯度學習演算法 -
The traditional neural networks, bp networks, are subject to three hardly conquerable drawbacks in network training and network design a long time, including slow training speed, the training tending to sinking into local minimum and the trained networks having poor generalization capability
傳統的神經網路（ bp網路）在網路訓練和網路設計上長期受困於三個難以克服的缺陷，即網路訓練速度慢、訓練易陷入局部極小點和網路學習的推廣性能差。 -
Livingstone d j, manallack d t, tekto i v. data modeling with neural networks : adventages and limitations [ j ]. comput aided mol design, 1997 ( 135 ) : 11
閻平凡，張長水.人工神經網路與模擬進化計算[ m ] .北京:清華大學出版社， 2000 -
Detection of stock market dark horse using bp neural networks
神經網路捕捉股市黑馬初探 -
Rbf neural networks applied in soft - measuring of distillation columns
徑向基函數神經網路在精餾塔軟測量中的應用 -
Knowledge discovery in databases ( kdd ) is a multidisciplinary field, drawing work from areas including database technology, artificial intelligence, machine learning, statistics, neural networks, and pattern recognition
數據庫中的知識發現（ knowledgediscoveryindatabases ， kdd ）是當前涉及人工智慧、數據庫等學科的一門非常活躍的研究領域。 -
Utilization of artificial neural networks in the identification of bats ' echolocation calls
人工神經網路在蝙蝠回聲定位叫聲識別方面的應用 -
Application of the neural networks to the epicenter locating of explosion earthquakes
神經網路方法在爆炸地震震中定位方面的應用 -
Through the analysis to the substance of running equations of networks, the evolutive theorem of neural networks was proved
通過對網路運行方程本質的分析，證明了神經網路演化定理。 -
We deduce frondose algorithm of three layers bp neural networks which is used in common, and discuss several important issues in designing neural networks which is used to forecast, for example, number of hidden layer, nerve cell number of hidden layer, epoch of learning, embryonic power value, decision of node number about input and outputo at the same time, this dissertation sums up things that conventional bp algorithm is improved on considering disadvantages of it
3推導了常用的三層bp神經網路具體演算法，討論了實際預測應用中神經網路設計方面的幾個重要問題，如隱層數、隱層神經元數、訓練次數、初始權值、輸入節點數以及輸出節點數的確定。同時，針對傳統bp演算法存在的各種各樣的缺點，文中綜述了對其改進的情況。 -
Secondly, the artificial neural networks and mixed evolutionary computation are employed into the mathematical simulation of complex geological structure, and with gis and visualization technique, the method of geological digital 3 - d modeling and visualization is presented. so, not only the functions of making geological section and querying spatial information could be achieved, but also the spatial distribution of geological structures and their complex relationship could be described visually. thereby an interactive and convenient way for engineering geological design could be actualized
（ 2 ）提出了復雜地質構造數學模擬的神經網路方法與混合進化方法，並利用gis技術和可視化技術，深入研究了數字地質三維建模及其可視化方法，實現了地質三維任意剖切、信息空間查詢與管理等功能，從而為直觀描述地質構造的空間展布及其相互間的復雜空間關系，以及快捷、交互地進行工程地質設計提供了新的途徑與手段。 -
Adopt two neural networks ; using principal component analysis based neural network ( gha ) to acquire three principal components and using simulated annealing ( sa ) and bp network to class and recognize the marrow cells
採用兩級神經網路，利用基於神經網路的gha演算法獲得圖象的三個主分量，然後採用模擬退火演算法和bp演算法進行細胞的分類識別，獲得了較好的識別效果。 -
Based on weights analysis of feedforward neural networks, a hierarchic decomposition neural networks method for solving this problem is provided
基於前饋神經網路的權重分析，提出一種基於神經網路的結構優化層次分解方法，較好地解決了這一問題。
分享友人