neural Networks and Deep Learning(簡體中文),比較經(jīng)典的深度學(xué)習(xí)入門教程。
標(biāo)簽: Networks Learning neural Deep and 簡體中文
上傳時間: 2016-11-09
上傳用戶:zhousui
If you are acquainted with neural networks, automatic control problems are good industrial applications and have a dynamic or evolutionary nature lacking in static pattern-recognition; control ideas are also prevalent in the study of the natural neural networks found in animals and human beings. If you are interested in the practice and theory of control, artificial neu- ral networks offer a way to synthesize nonlinear controllers, filters, state observers and system identifiers using a parallel method of computation.
標(biāo)簽: Control Systems neural For
上傳時間: 2020-06-10
上傳用戶:shancjb
本文擬借助于神經(jīng)網(wǎng)絡(luò)良好的逼近能力,實現(xiàn)永磁同步電機的無位置傳感器控制。 人工神經(jīng)網(wǎng)絡(luò)(neural Network)可以逼近任意復(fù)雜非線性映射,具有很強的自學(xué)習(xí)自適應(yīng)能力,十分適合于解決復(fù)雜的非線性控制問題。其中,BP神經(jīng)網(wǎng)絡(luò)是目前廣泛應(yīng)用的神經(jīng)網(wǎng)絡(luò)之一,得到了較為深入的研究,其結(jié)構(gòu)簡單,需要離線確定的參數(shù)少、泛化能力強、逼近精度高、實時性強,采用BP神經(jīng)網(wǎng)絡(luò)實現(xiàn)永磁同步電機的調(diào)速控制具有重要意義。 文中提出了基于BP神經(jīng)網(wǎng)絡(luò)的永磁同步電機自適應(yīng)調(diào)速控制策略,建立了一種包含辨識網(wǎng)絡(luò)和控制網(wǎng)絡(luò)的雙神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)控制系統(tǒng)。辨識網(wǎng)絡(luò)在線動態(tài)辨識系統(tǒng)輸出并對控制網(wǎng)絡(luò)參數(shù)進行調(diào)整,控制網(wǎng)絡(luò)與PI控制方法相結(jié)合實現(xiàn)永磁同步電機自適應(yīng)轉(zhuǎn)速控制。仿真結(jié)果表明,該系統(tǒng)動態(tài)響應(yīng)快、實時性較強、精度較高。 文中提出了一種基于混合訓(xùn)練算法的BP神經(jīng)網(wǎng)絡(luò)永磁同步電機無位置傳感器控制方法。采用混沌優(yōu)化和梯度下降法相結(jié)合的混合算法對BP神經(jīng)網(wǎng)絡(luò)進行離線訓(xùn)練后,將其用于永磁同步電機的轉(zhuǎn)子位置角在線估計。結(jié)果表明,該訓(xùn)練算法可以有效地加快神經(jīng)網(wǎng)絡(luò)收斂速度,且估計的轉(zhuǎn)子位置角誤差較小、精度較高。 文中建立了以TMS320F2812芯片為核心的永磁同步電機調(diào)速控制系統(tǒng),并進行了相應(yīng)的軟硬件設(shè)計,為實現(xiàn)永磁同步電機的各種控制策略奠定了實驗基礎(chǔ)。DSP控制系統(tǒng)為神經(jīng)網(wǎng)絡(luò)訓(xùn)練提供樣本,為研究永磁同步電機的自適應(yīng)調(diào)速控制和轉(zhuǎn)子位置角估計創(chuàng)造了條件。
標(biāo)簽: BP神經(jīng)網(wǎng)絡(luò) 永磁同步電機 自適應(yīng)控制
上傳時間: 2013-05-23
上傳用戶:1101055045
永磁同步電機(Permanent Magnet Synchronous Motor)因功率密度大、效率高、過載能力強、控制性能優(yōu)良等優(yōu)點,在中小容量調(diào)速系統(tǒng)和高精度調(diào)速場合發(fā)展迅速。但由于永磁同步電機的磁場具有獨特的交叉耦合和交叉飽和現(xiàn)象,且其控制系統(tǒng)是一個強非線性、時變和多變量系統(tǒng),要實現(xiàn)高精度調(diào)速就需對其控制策略進行深入研究。 永磁同步電機調(diào)速系統(tǒng)中,位置傳感器的存在使得系統(tǒng)成本增加、結(jié)構(gòu)復(fù)雜、可靠性降低,所以永磁同步電機的無位置傳感器控制成為一個新的研究熱點。本文擬借助于神經(jīng)網(wǎng)絡(luò)良好的逼近能力,實現(xiàn)永磁同步電機的無位置傳感器控制。 人工神經(jīng)網(wǎng)絡(luò)(neural Network)可以逼近任意復(fù)雜非線性映射,具有很強的自學(xué)習(xí)自適應(yīng)能力,十分適合于解決復(fù)雜的非線性控制問題。其中,BP神經(jīng)網(wǎng)絡(luò)是目前廣泛應(yīng)用的神經(jīng)網(wǎng)絡(luò)之一,得到了較為深入的研究,其結(jié)構(gòu)簡單,需要離線確定的參數(shù)少、泛化能力強、逼近精度高、實時性強,采用BP神經(jīng)網(wǎng)絡(luò)實現(xiàn)永磁同步電機的調(diào)速控制具有重要意義。 文中提出了基于BP神經(jīng)網(wǎng)絡(luò)的永磁同步電機自適應(yīng)調(diào)速控制策略,建立了一種包含辨識網(wǎng)絡(luò)和控制網(wǎng)絡(luò)的雙神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)控制系統(tǒng)。辨識網(wǎng)絡(luò)在線動態(tài)辨識系統(tǒng)輸出并對控制網(wǎng)絡(luò)參數(shù)進行調(diào)整,控制網(wǎng)絡(luò)與PI控制方法相結(jié)合實現(xiàn)永磁同步電機自適應(yīng)轉(zhuǎn)速控制。仿真結(jié)果表明,該系統(tǒng)動態(tài)響應(yīng)快、實時性較強、精度較高。 文中提出了一種基于混合訓(xùn)練算法的BP神經(jīng)網(wǎng)絡(luò)永磁同步電機無位置傳感器控制方法。采用混沌優(yōu)化和梯度下降法相結(jié)合的混合算法對BP神經(jīng)網(wǎng)絡(luò)進行離線訓(xùn)練后,將其用于永磁同步電機的轉(zhuǎn)子位置角在線估計。結(jié)果表明,該訓(xùn)練算法可以有效地加快神經(jīng)網(wǎng)絡(luò)收斂速度,且估計的轉(zhuǎn)子位置角誤差較小、精度較高。 文中建立了以TMS320F2812芯片為核心的永磁同步電機調(diào)速控制系統(tǒng),并進行了相應(yīng)的軟硬件設(shè)計,為實現(xiàn)永磁同步電機的各種控制策略奠定了實驗基礎(chǔ)。DSP控制系統(tǒng)為神經(jīng)網(wǎng)絡(luò)訓(xùn)練提供樣本,為研究永磁同步電機的自適應(yīng)調(diào)速控制和轉(zhuǎn)子位置角估計創(chuàng)造了條件。
標(biāo)簽: BP神經(jīng)網(wǎng)絡(luò) 永磁同步電機 自適應(yīng)控制
上傳時間: 2013-07-03
上傳用戶:kakuki123
java人工股市源碼,用了GA(Genetic Algorithm)和ANN(Artificial neural Network)。內(nèi)附程序詳細說明,強烈推薦!
上傳時間: 2015-02-26
上傳用戶:TRIFCT
Description: C4.5Rule-PANE is a rule learning method which could generate accurate and comprehensible symbolic rules, through regarding a neural network ensemble as a pre-process of a rule inducer. Reference: Z.-H. Zhou and Y. Jiang. Medical diagnosis with C4.5 rule preceded by artificial neural network ensemble. IEEE Transactions on Information Technology in Biomedicine, 2003, vol.7, no.1, pp.37-42. 使用神經(jīng)網(wǎng)絡(luò)集成方法診斷糖尿病,肝炎,乳腺癌癥的案例研究.
標(biāo)簽: comprehensibl Description Rule-PANE accurate
上傳時間: 2013-11-30
上傳用戶:wcl168881111111
The purpose of this computer program is to allow the user to construct, train and test differenttypes of artificial neural networks. By implementing the concepts of templates, inheritance andderived classes from C++ object oriented programming, the necessity for declaring multiple largestructures and duplicate attributes is reduced. Utilizing dynamic binding and memory allocationafforded by C++, the user can choose to develop four separate types of neural networks:
標(biāo)簽: differenttype construct computer purpose
上傳時間: 2013-12-06
上傳用戶:13517191407
The Netlab toolbox is designed to provide the central tools necessary for the simulation of theoretically well founded neural network algorithms and related models for use in teaching, research and applications development. It contains many techniques which are not yet available in standard neural network simulation packages
標(biāo)簽: simulation necessary the designed
上傳時間: 2013-12-11
上傳用戶:hj_18
MULTIDIMENSIONAL SCALING in matlab by Mark Steyvers 1999 %needs optimization toolbox %Modified by Bruce Land %--Data via globals to anaylsis programs %--3D plotting with color coded groups %--Mapping of MDS space to spike train temporal profiles as described in %Aronov, et.al. "neural coding of spatial phase in V1 of the Macaque" in %press J. Neurophysiology
標(biāo)簽: MULTIDIMENSIONAL optimization Modified Steyvers
上傳時間: 2015-08-26
上傳用戶:kytqcool
ICA介紹課件。There has been a wide discussion about the application of Independence Component Analysis (ICA) in Signal Processing, neural Computation and Finance, first introduced as a novel tool to separate blind sources in a mixed signal. The Basic idea of ICA is to reconstruct from observation sequences the hypothesized independent original sequences
標(biāo)簽: Independence application discussion Component
上傳時間: 2016-01-12
上傳用戶:AbuGe
蟲蟲下載站版權(quán)所有 京ICP備2021023401號-1