back propagation algorithm

"back propagation algorithm"的翻譯和解釋

"查查詞典"手機(jī)版

千萬人都在用的超大詞匯詞典翻譯APP

例句與用法

Based on the integration of fuzzy logic system and neural networks the thesis constructs a fuzzy neural network controller , which is used in ship course self - studying adaptive control system . because the fuzzy logic system is realized in neural network , the fuzzy neural network controller " s self - studying ability is raised greatly . substituting improved genetic algorithm for back propagation algorithm in fuzzy neural network controller ship course fuzzy neural network control system " s real - time ability is raised
針對(duì)模糊邏輯系統(tǒng)有很強(qiáng)的知識(shí)表達(dá)能力和邏輯推理能力，但自學(xué)習(xí)能力比較差，而人工神經(jīng)網(wǎng)絡(luò)在自學(xué)習(xí)和函數(shù)逼近方面又具有獨(dú)特的優(yōu)越性，將兩者結(jié)合，用神經(jīng)網(wǎng)絡(luò)來實(shí)現(xiàn)模糊邏輯系統(tǒng)，構(gòu)造了一個(gè)基于模糊神經(jīng)網(wǎng)絡(luò)控制武漢理工大學(xué)博士學(xué)位論文器的船舶航向自學(xué)習(xí)型自適應(yīng)控制系統(tǒng)，提出用改進(jìn)的遺傳算法代替神經(jīng)網(wǎng)絡(luò)中經(jīng)典的bp算法實(shí)現(xiàn)模糊神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)，綜合船舶航向控制性能和節(jié)能要求，建立了系統(tǒng)的適應(yīng)度函數(shù)。
For the planar gap and the tridimensional vertical bend of shielded cpw , fdtd simulations are carried out to produce training and testing samples and error - back propagation algorithm is used to train the multilayer perceptron neural networks ( mlpnns ) . rapid and accuracy cad models of these structures are successfully obtained for the first time
對(duì)于屏蔽cpw的間隙不連續(xù)性和垂直互連不連續(xù)性結(jié)構(gòu)，采用fdtd方法獲取訓(xùn)練和檢測(cè)樣本數(shù)據(jù)，用回傳算法訓(xùn)練多層感知器，首次成功地獲得了這些結(jié)構(gòu)快速、準(zhǔn)確的cad模型。
Based on the historical space forecast data and corresponding actual data provided by a global semiconductor assembly and test company , the uncertainty of space planning was defined . during this analysis process , linear regression , grey prediction , neural network back propagation algorithm and confidence interval were applied , respectively , to define the uncertainty . compared with those methods , the confidence interval of historical space forecast error , calculated by mathematical statistics , was the reasonable method to define the space forecasting uncertainty
本文從半導(dǎo)體工廠長(zhǎng)期生產(chǎn)能力計(jì)劃的頂層即廠房生產(chǎn)面積的計(jì)劃展開,對(duì)一跨國(guó)半導(dǎo)體封裝測(cè)試公司提供的廠房生產(chǎn)面積的長(zhǎng)期歷史預(yù)測(cè)數(shù)據(jù)以及對(duì)應(yīng)的真實(shí)數(shù)據(jù)進(jìn)行分析,采用線性回歸,灰預(yù)測(cè),神經(jīng)網(wǎng)絡(luò)bp算法,基于數(shù)理統(tǒng)計(jì)的置信區(qū)間的求解等方法分別定義廠房生產(chǎn)面積預(yù)測(cè)的不確定度,經(jīng)多種方法的比較得出,基于數(shù)理統(tǒng)計(jì)方法求解出的生產(chǎn)面積歷史預(yù)測(cè)誤差置信區(qū)間能直觀清楚地標(biāo)定不確定度。
The simulation results indicate the capability of genetic algorithm in fast and steady learning of neural networks , guaranteeing a global convergence and overcoming some shortcomings of traditional error back propagation algorithms , meanwhile prove that this neural networks adaptive control structure is effective to many control problems and it is easy for us to programme and employ the method in the practical system
仿真結(jié)果表明遺傳算法能夠快速穩(wěn)定地學(xué)習(xí)神經(jīng)網(wǎng)絡(luò)，保證全局收斂西安理工大學(xué)碩士學(xué)位論文并且能夠克服傳統(tǒng)誤差反傳算法的一些缺點(diǎn)，也證明了這種神經(jīng)網(wǎng)絡(luò)自適應(yīng)控制結(jié)構(gòu)可以有效解決系統(tǒng)中存在的控制難題，同時(shí)編程容易，便于在實(shí)際系統(tǒng)中應(yīng)用。
Neural network control is an important mode of intelligent control , and it is widely used in branches of control science , , first , the architecture and the learning rule ( error back propagation algorithm ) of multiplayered neural network which is widely used in control system are presentedo especially , the paper refers to the architecture of diagonal recurrent neural network and its learning algorithm - - - - - recurrent prediction error algorithm because of its faster convergence with low computing costo next , before introducing the neural network control to the double close loop dc driver system , the controllers of current and velocity loop are designed using engineering design approach after analysis of the system , , simulation models of the system are created
神經(jīng)網(wǎng)絡(luò)控制是智能控制的重要方式之一，它廣泛應(yīng)用于自動(dòng)控制學(xué)科各個(gè)領(lǐng)域。本文首先敘述了控制系統(tǒng)中常用的多層前饋網(wǎng)絡(luò)結(jié)構(gòu)及算法( bp算法) ，特別提及了能夠較好描述系統(tǒng)動(dòng)態(tài)性能的對(duì)角遞歸神經(jīng)網(wǎng)絡(luò)和在用遞推預(yù)報(bào)誤差算法訓(xùn)練drnn時(shí)取得了較快的收斂速度。其次，應(yīng)用工程方法分析設(shè)計(jì)了tf - 1350糖分離機(jī)的電流、轉(zhuǎn)速雙閉環(huán)直流調(diào)速系統(tǒng)的控制器，作為引入神經(jīng)網(wǎng)絡(luò)控制的設(shè)計(jì)基礎(chǔ)，并建立了系統(tǒng)的仿真模型。
Firstly , on the basic of normal error back propagation algorithm ( bp a1gorithm ) , the model was added the inertia impulse item in the updating formula for weight , and then let learning rate and inertia parameter adjust ll self - adaptively , so the improved bp algorithm ( improved bp algorithm , ibp algorithm ) formed
首先，該模型在誤差反向傳播算法( bp算法)的基礎(chǔ)上，在網(wǎng)絡(luò)權(quán)值更新公式中添加慣性沖量項(xiàng)，并對(duì)學(xué)習(xí)率和慣量因子進(jìn)行自適應(yīng)調(diào)整，從而形成bp改進(jìn)算法( improvedbp算法，簡(jiǎn)稱ibp算法) 。