Feed-forward artificial neural networks: Applications to spectroscopy

被引：63
作者：
Cirovic, DA
机构：
[1] Chemometrics Grp. the Sch. of Chem., University of Bristol, Bristol BS8 1TS, Cantock's Close
来源：
TRAC-TRENDS IN ANALYTICAL CHEMISTRY | 1997年 / 16卷 / 03期
关键词：
D O I：
10.1016/S0165-9936(97)00007-1
中图分类号：
O65 [分析化学];
学科分类号：
070302 ; 081704 ;
摘要：
Applications of multi-layer feed-forward artificial neural networks (ANN) to spectroscopy are reviewed. Network architecture and training algorithms are discussed. Backpropagation, the most commonly used training algorithm, is analyzed in greater detail. The following types of applications are considered: data reduction by means of neural networks, pattern recognition, multivariate regression, robust regression, and handling of instrumental drifts.
引用
收藏
页码：148 / 155
页数：8
相关论文
共 36 条
[1]  
[Anonymous], 1989, MULTIVARIATE CALIBRA
[2]   ADAPTIVE, GLOBAL, EXTENDED KALMAN FILTERS FOR TRAINING FEEDFORWARD NEURAL NETWORKS [J].
BLANK, TB ;
BROWN, SD .
JOURNAL OF CHEMOMETRICS, 1994, 8 (06) :391-407
[3]   OPTIMAL MINIMAL NEURAL INTERPRETATION OF SPECTRA [J].
BORGGAARD, C ;
THODBERG, HH .
ANALYTICAL CHEMISTRY, 1992, 64 (05) :545-551
[4]   DATA-PROCESSING BY NEURAL NETWORKS IN QUANTITATIVE CHEMICAL-ANALYSIS [J].
BOS, M ;
BOS, A ;
VANDERLINDEN, WE .
ANALYST, 1993, 118 (04) :323-328
[5]   FOURIER-TRANSFORMS - USE, THEORY AND APPLICATIONS TO SPECTROSCOPIC AND RELATED DATA [J].
BRERETON, RG .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1986, 1 (01) :17-31
[6]  
BROWN SD, 1996, COMPUTER ASSISTED AN, P107
[7]   FEEDFORWARD NEURAL NETWORKS IN CHEMISTRY - MATHEMATICAL SYSTEMS FOR CLASSIFICATION AND PATTERN-RECOGNITION [J].
BURNS, JA ;
WHITESIDES, GM .
CHEMICAL REVIEWS, 1993, 93 (08) :2583-2601
[8]   A ROBUST BACK-PROPAGATION LEARNING ALGORITHM FOR FUNCTION APPROXIMATION [J].
CHEN, DS ;
JAIN, RC .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (03) :467-479
[9]   A NONLINEAR PLS MODEL [J].
FRANK, IE .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1990, 8 (02) :109-119
[10]  
FRANK IE, 1994, INCINC 94 1 INT CHEM
1234