東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Mathematical theory of neural learni...

Xiong, Momiao.

FindBook

Google Book

Amazon

博客來

Mathematical theory of neural learning and its applications to statistics and molecular biology.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Mathematical theory of neural learning and its applications to statistics and molecular biology./
作者:	Xiong, Momiao.
面頁冊數:	189 p.
附註:	Directors: Hubert J. Chen; Jonathan Arnold.
Contained By:	Dissertation Abstracts International54-09B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9404699

Mathematical theory of neural learning and its applications to statistics and molecular biology.
Xiong, Momiao.

Mathematical theory of neural learning and its applications to statistics and molecular biology. - 189 p.

Directors: Hubert J. Chen; Jonathan Arnold.

Thesis (Ph.D.)--University of Georgia, 1993.

The neural learning theory is also applied to a physical mapping problem in molecular biology and an attempt to prove the consistency of a neural learning algorithm in this specific setting is established.Subjects--Topical Terms:

769149
Artificial Intelligence.

Mathematical theory of neural learning and its applications to statistics and molecular biology.
LDR:04054nam 2200349 a 45 001 930033
005 20110427
008 110427s1993 eng d
035 $a (UnM)AAI9404699
035 $a AAI9404699
040 $a UnM $c UnM
100 1 $a Xiong, Momiao. $3 1253516
245 1 0 $a Mathematical theory of neural learning and its applications to statistics and molecular biology.
300 $a 189 p.
500 $a Directors: Hubert J. Chen; Jonathan Arnold.
500 $a Source: Dissertation Abstracts International, Volume: 54-09, Section: B, page: 4763.
502 $a Thesis (Ph.D.)--University of Georgia, 1993.
520 $a The neural learning theory is also applied to a physical mapping problem in molecular biology and an attempt to prove the consistency of a neural learning algorithm in this specific setting is established.
520 $a In recent years, considerable progress in neural network research have been made and applications of neural networks have been extended to a large number of different disciplines, including biology, psychology, physics, mathematics, statistics, engineering, operations research and computer science. The result is a very interdisciplinary and inspiring research area, and of course a variety of different terminologies, concepts and notations. Also there has been increasing interest in building a complex neural network which consist of various modular neural subnetworks to carry out increasingly sophisticated tasks.
520 $a This dissertation is devoted to the development of a unified mathematical theory of neural learning to form the basis for describing the network topology, for constructing learning rules by nonsmooth analysis and a dynamical system approach to constrained optimization, and for synthesizing hierarchically organized modular neural networks. This dissertation also illustrates applications of neural networks to forecasting time series and physical mapping in molecular biology.
520 $a By introducing a neural learning function for various artificial neural network models, learning is represented as an optimization process subject to constraints inherent in a particular problem. Transforming a constrained optimization problem into an unconstrained optimization problem through Lagrange multipliers, for example, may lead to a nonsmooth learning function. Nonsmooth analysis and a differential inclusion for solving nonsmooth optimization problems are introduced to form the theoretical basis for constructing learning rules. Several stability theorems for a learning process are proven to guarantee that the learning function is minimized as the neural network evolves, i.e. the artificial network performs optimally. A neural network model based on differential-algebraic equations (DAEs) is also proposed. The global and local convergence properties of neural learning algorithms for constrained optimization problems are analyzed. Simulations of neutral network models for constrained optimization problems are carried out. It is demonstrated that neural network models may provide a good alternative method to solving constrained optimization problems.
520 $a As an application, a general nonlinear autoregressive-integrated moving average model based on neural networks is proposed for forecasting time series and a new dynamic backpropagation learning procedure is introduced. The results of a forecasting competition between a neural network model and a Box-Jenking forecasting method are also presented. Simulation results on several examples reveal that forecasting by the neural network model outperforms the Box-Jenkins model in terms of mean absolute error and mean percentage forecast error.
590 $a School code: 0077.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Biology, Genetics. $3 1017730
650 4 $a Computer Science. $3 626642
650 4 $a Statistics. $3 517247
690 $a 0369
690 $a 0463
690 $a 0800
690 $a 0984
710 2 0 $a University of Georgia. $3 515076
773 0 $t Dissertation Abstracts International $g 54-09B.
790 $a 0077
790 1 0 $a Arnold, Jonathan, $e advisor
790 1 0 $a Chen, Hubert J., $e advisor
791 $a Ph.D.
792 $a 1993
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9404699