南開科技大學圖書館 |

Language: 繁體中文

說明(常見問題)

南開科技大學

圖書館首頁

編目中圖書申請

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Advanced architecture and training a...

Cai, Xindi.

Advanced architecture and training algorithms for recurrent neural networks.

紀錄類型:	書目-電子資源 : 單行本
正題名/作者:	Advanced architecture and training algorithms for recurrent neural networks./
作者:	Cai, Xindi.
面頁冊數:	76 p.
附註:	Source: Dissertation Abstracts International, Volume: 67-08, Section: B, page: 4588.
Contained By:	Dissertation Abstracts International67-08B.
標題:	Engineering, Electronics and Electrical. -
電子資源:	Download PDF (下載PDF全文)
ISBN:	9780542828867

Advanced architecture and training algorithms for recurrent neural networks.
Cai, Xindi.

Advanced architecture and training algorithms for recurrent neural networks. - 76 p.

Source: Dissertation Abstracts International, Volume: 67-08, Section: B, page: 4588.

Thesis (Ph.D.)--University of Missouri - Rolla, 2006.

Recurrent neural networks (RNN) attract considerable interest in computational intelligence fields because of its superior power in processing spatio-temporal data and time-varying signals.

ISBN: 9780542828867Subjects--Topical Terms:

170927
Engineering, Electronics and Electrical.

Advanced architecture and training algorithms for recurrent neural networks.
LDR:03030nmm 2200325 4500 001 1000004913
005 20070601084731.5
008 070601s2006 eng d
020 $a 9780542828867
035 $a (UnM)AAI3229176
035 $a AAI3229176
040 $a UnM $c UnM{me_controlnum}
100 1 $a Cai, Xindi. $3 1000006067
245 1 0 $a Advanced architecture and training algorithms for recurrent neural networks.
300 $a 76 p.
500 $a Source: Dissertation Abstracts International, Volume: 67-08, Section: B, page: 4588.
500 $a Adviser: Donald C. Wunsch, II.
502 $a Thesis (Ph.D.)--University of Missouri - Rolla, 2006.
520 $a Recurrent neural networks (RNN) attract considerable interest in computational intelligence fields because of its superior power in processing spatio-temporal data and time-varying signals.
520 $a Traditionally, the recurrency of a neural network occurs between input samples along the time axis. The simultaneous recurrent network (SRN) extends the recurrent property to the spatial dimension. Presenting the feedback information with the same input vector to the network illustrates the transient properties of the system, which helps to trace the error propagation and facilitates the training at last. Backpropagation through time and extended Kalman filter are proved to be suitable gradient-based training algorithms for RNN.
520 $a Population based algorithms provide an alternative solution for RNN training when the gradient information is costly to obtain, or even unavailable. The evolutionary training employs stochastic search algorithms to find a near-optimal solution. Particle swarm optimization (PSO) and evolutionary algorithm (EA) are two successful approaches among many variants of evolutionary training methods. Despite utilizing similar evolution procedure, PSO and EA concentrate on different search techniques during the evolution, which leads to a faster convergence. In PSO, particles are also sharing the search information through a global best solution. While in EA, the selection pressure forces each individual to find a better position for survival; and the mutation factor helps the population to maintain a good level of diversity. An innovative hybrid PSO-EA algorithm discussed in this dissertation inherits the advantages of both PSO and EA, i.e., the cooperation and competition, by integrating evolutionary operators, such as selection and mutation, into the standard PSO.
520 $a The architecture and training methods discussed above have achieved good performance in solving the challenging real world applications, such as car engine classification, game of Go and time series prediction.
590 $a School code: 0135.
650 4 $a Engineering, Electronics and Electrical. $3 170927
650 4 $a Artificial Intelligence. $3 165300
650 4 $a Computer Science. $3 1000005419
690 $a 0544
690 $a 0800
690 $a 0984
710 2 0 $a University of Missouri - Rolla. $3 1000005559
773 0 $t Dissertation Abstracts International $g 67-08B.
790 1 0 $a Wunsch, Donald C., II, $e advisor
790 $a 0135
791 $a Ph.D.
792 $a 2006
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3229176 $z Download PDF (下載PDF全文)