feed-forward neural network造句
例句與造句
- Feed - forward neural network based on gaussnewton - nl2sol algorithm and its application
法的前饋神經(jīng)網(wǎng)絡(luò)及應(yīng)用 - Chapter 2 focuses on weight learning and structure learning of multi - layer feed - forward neural networks
主要研究前向神經(jīng)網(wǎng)絡(luò)的權(quán)值學(xué)習(xí)和結(jié)構(gòu)學(xué)習(xí)方法。 - This paper is mainly devoted to the principle and the implemental algorithms of qualitative learning for feed - forward neural networks ( fnns )
本文主要研究前向神經(jīng)網(wǎng)絡(luò)定性學(xué)習(xí)的原理和學(xué)習(xí)算法。 - Wavelet neural network ( wnn ) is a novel feed - forward neural network based on wavelet theory , and it possesses several excellent features
摘要小波神經(jīng)網(wǎng)絡(luò)是建立在小波理論基礎(chǔ)上的一種新型前饋神經(jīng)網(wǎng)絡(luò)，具有許多優(yōu)良特性。 - Based on rbf neural network and perceptron neural network , a four - layer feed - forward neural network named radial basis perceptron ( rbp ) network is presented
基于rbf網(wǎng)絡(luò)和感知器( perceptron )網(wǎng)絡(luò)建立一四層前饋神經(jīng)網(wǎng)絡(luò)?徑向基感知器( radialbasisperceptron ， rbp )網(wǎng)絡(luò)。 - It's difficult to find feed-forward neural network in a sentence. 用feed-forward neural network造句挺難的
- The feed - forward neural network is provided to recognizing the currency values , which makes use of the capability to extract features automatically and the error tolerance of neural networks
利用神經(jīng)網(wǎng)絡(luò)自動特征提取能力和容錯特性，提出使用前饋神經(jīng)網(wǎng)絡(luò)對面值進(jìn)行識別。 - Firstly , studied feed - forward neural network and put forward a new algorithm on bp network , called bp algorithm based on robust error function ( bparef ) , and the algorithm is proved to be effective for approaching nonlinear system
首先研究了前饋神經(jīng)網(wǎng)絡(luò)，提出了基于魯棒誤差函數(shù)的bp神經(jīng)網(wǎng)絡(luò)的算法，并且驗證了其對非線性系統(tǒng)逼近的有效性。 - In the last of this paper we apply our algorithms to the learning of feed - forward neural network , and get some new learning algorithms . we also give some numerical experiments to compare our algorithms with others
最后，將得到的這些優(yōu)化加速收斂方法應(yīng)用到了多層前饋神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)過程，給出了加速收斂的bp算法，通過實(shí)際神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)問題驗證了工作的成效。 - Recently a covering method for feed - forward neural network design has been proposed by professor zhang ling . based on the sphere neighborhood model , this method transforms the design of neural classifiers to a geometrical covering problem
近來張鈴教授提出了一種前饋神經(jīng)網(wǎng)絡(luò)設(shè)計的覆蓋方法，它以球面領(lǐng)域模型為基礎(chǔ)，使得神經(jīng)網(wǎng)絡(luò)的設(shè)計轉(zhuǎn)化為幾何覆蓋問題。 - To overcome the limitations of general fnns and bp algorithm , this thesis introduced a hybrid feed - forward neural network , which is composed of a linear model and a general multi - layer fnn , and proposed a new learning algorithm for the hybrid fnn
其次，針對bp網(wǎng)絡(luò)存在的缺陷，結(jié)合前向神經(jīng)網(wǎng)絡(luò)和線性最小二乘法的優(yōu)點(diǎn)，構(gòu)造了一種基于混合結(jié)構(gòu)的神經(jīng)網(wǎng)絡(luò)，提出了相應(yīng)的非迭代的快速學(xué)習(xí)算法。 - In this thesis , some kinds of learning algorithms of feed - forward neural network have been analyzed ; later a scaled conjugate gradient algorithm is presented to train network , furthermore , modified training methods have been provided to improve the neural network performance
在分析比較了幾種前饋神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)算法后，提出尺度共軛梯度算法對網(wǎng)絡(luò)進(jìn)行訓(xùn)練，并針對現(xiàn)有網(wǎng)絡(luò)訓(xùn)練方法提出了改進(jìn)。 - This thesis , based on extraction and analysis on the feature of currency , presents the feed - forward neural network to recognizing the currency values , combines with the statistical analysis to recognize the fake and forms a set of methods for currency recognition
本文在對貨幣特征精確提取和分析的基礎(chǔ)上，提出將前饋神經(jīng)網(wǎng)絡(luò)應(yīng)用于貨幣識別問題，并結(jié)合統(tǒng)計分析方法，形成一套貨幣識別的系統(tǒng)方法。 - Based on the analysis and processing of the digital speckle pattern , the translation and rotation invariant features are discovered , and a one - step feed - forward neural network is creatively proposed which makes it possible to realize the intelligent recognition of interface defects
通過對數(shù)學(xué)散斑條紋的分析與處理，找出了能代表條紋信息的移位不變與旋轉(zhuǎn)不變特征值? ?最大斜率，進(jìn)而構(gòu)造一種新的網(wǎng)絡(luò)模型，即單步前饋式三層網(wǎng)絡(luò)系統(tǒng).率先實(shí)現(xiàn)了把神經(jīng)網(wǎng)絡(luò)系統(tǒng)用在數(shù)字散斑無損檢測之中，完成了神經(jīng)網(wǎng)絡(luò)系統(tǒng)對粘接界面缺陷的智能辨識 - First , this thesis reviewed the development and applications of anns , and it presented some typical anns which are widely used . especially , it analyzed multi - layer feed - forward neural networks ( fnns ) and their traditional learning algorithm , back propagation ( bp ) algorithm , because fnns are the most common used anns
本文首先介紹了神經(jīng)網(wǎng)絡(luò)理論的發(fā)展歷史和應(yīng)用領(lǐng)域，然后介紹了人工神經(jīng)元網(wǎng)絡(luò)的特點(diǎn)及目前應(yīng)用比較廣泛的幾種典型的神經(jīng)網(wǎng)絡(luò)，并重點(diǎn)分析了當(dāng)今最流行的bp網(wǎng)絡(luò)的特性。 - Later on , after elaborating the disadvantages of the old methods in detecting and recognizing moving objects , a series of corresponding approaches are proposed , such as grid scan , local tracking bug and dynamic window in object tracing to reduce the huge data needed to be processed , maximum and minimum for selecting a proper segmentation threshold and improved conversion from rgb model to hsv and so on to decrease the influence of inhomogeneous lighting and the color noise , a bilinear interpolation in each quadrant to eliminate the bad effect on the recognition precise because of the distortions of the camera . after that , much emphasis is given on application study in pattern recognition with a feed - forward neural network . both the basic bp algorithm and improved bp algorithm in the study process are described in detail , and the later is used to quicken convergence speed and improve validity of the network
然后，分析和闡明了傳統(tǒng)的運(yùn)動目標(biāo)檢測方法的不足，并在此基礎(chǔ)上結(jié)合研究中的實(shí)際實(shí)驗環(huán)境，提出了一系列解決方法，包括針對降低龐大數(shù)據(jù)量而提出的網(wǎng)格掃描、局部“跟蟲”追蹤和動態(tài)窗口掃描等目標(biāo)檢測方法，針對實(shí)驗環(huán)境中光照不均和顏色干擾提出基于人機(jī)交互的最大最小值閾值選取方法和引入改進(jìn)的rgb模型到hsv模型的轉(zhuǎn)換方法，為消除圖像畸變對識別精度的惡劣影響而采用的通過控制點(diǎn)進(jìn)行雙線性插值進(jìn)行畸變校正的方法；緊接著，概述了神經(jīng)網(wǎng)絡(luò)的發(fā)展歷史和幾種常用神經(jīng)網(wǎng)絡(luò)模型的特點(diǎn)，重點(diǎn)研究了前饋型神經(jīng)網(wǎng)絡(luò)在模式識別中的應(yīng)用問題，詳細(xì)闡述了基本的bp算法和學(xué)習(xí)過程中bp算法的改進(jìn)，從而使網(wǎng)絡(luò)收斂速度更快，解決問題更有效，并在此基礎(chǔ)上，設(shè)計了一個基于bp神經(jīng)網(wǎng)絡(luò)的運(yùn)動目標(biāo)識別系統(tǒng)，給出了實(shí)驗結(jié)果。
更多例句： 下一頁