Feed-forward neural networks in chemistry: mathematical systems for classification and pattern recognition

Burns, John A.; Whitesides, George M.

doi:10.1021/cr00024a001

Cited by 173 publications

(108 citation statements)

References 42 publications

(55 reference statements)

Supporting

Mentioning

107

Contrasting

Unclassified

Order By: Relevance

“…Most of these methods are linear (linear statistical models, k-nearest neighbours) and are poorly suited for infrared spectra classification [9]. Moreover, statistical methods have difficulties handling the high interdependence of spectral variables.…”

Section: Introductionmentioning

confidence: 99%

Clustering of infrared spectra with Kohonen networks

Cleva

Cachet²,

Cabrol‐Bass³

1999

Analusis

View full text Add to dashboard Cite

Abstract. The design of systems for spectral data interpretation requires clustering of chemical compounds based on their spectral characteristics. Kohonen networks have been shown to be efficient tools to achieve this clustering. These auto-organising systems perform a mapping between a high-dimensional variable space and a two-dimensional one. An application to infrared spectra of organic compounds is presented here. The non-supervised learning algorithm used allows classification of compounds by spectral characteristics without a priori knowledge. An analysis of the distribution of spectra on the resulting maps is used to build models for predicting the presence or absence of specific structural features. The performance of the models in recognising structural features is discussed and compared with the prediction of a multilayered feed forward network (MLFFN). Localisation of compounds wrongly classified by the MLFFN on the Kohonen maps allows to establish a link between the supervised and the unsupervised approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Clustering of infrared spectra with Kohonen networks

Cleva

Cachet²,

Cabrol‐Bass³

1999

Analusis

View full text Add to dashboard Cite

show abstract

“…The theoretical foundation and the applications of ANNs in chemistry, mainly in the pattern recognition area, have been extensively reviewed. [23,24] The chiral analysis problem in this study can be solved with an ANN program. The general procedure included three steps.…”

Section: Resultsmentioning

confidence: 99%

Two Methods for the Determination of Enantiomeric Excess and Concentration of a Chiral Sample with a Single Spectroscopic Measurement

Zhu

Shabbir

Anslyn

2006

Chemistry A European J

View full text Add to dashboard Cite

The previously established enantioselective indicator–displacement assays (eIDAs) for the determination of concentration and enantiomeric excess (ee) require two spectroscopic measurements for each chiral sample. To further simplify the operation of eIDAs, we now introduce two innovative analytical methods, both of which utilize a dual‐chamber quartz cuvette, which reduces the number of spectroscopic measurements from two to one. An attractive feature of this cuvette is that the concentration‐ and ee‐dependent absorption data can be collected at the isosbestic points or transparent regions of the spectra recorded in each individual chamber, thereby reflecting optical changes that occur in the other chamber. Therefore, two independent equations, which are needed to solve the values of the two independent variables—concentration and ee—can be established with only a single spectroscopic measurement. The first method takes advantage of this feature in conjunction with a judicious choice of indicator/host combinations to generate concentration‐ and ee‐dependent calibration curves. Our second method removes the requirement to measure equilibrium constants and molar absorptivities altogether through the use of artificial neural networks (ANNs). The most frequently used three‐layer feed‐forward network is generated, which relates the absorption data to concentration and ee of the samples by training with a back propagation procedure. Here, the data collection is not limited to the isosbestic points or transparent regions. Both approaches enabled accurate and rapid determination of concentration and ee of chiral samples. The technology removes the relative difficulty, which is the need for two separate measurements for concentration and ee respectively, of analyzing chiral samples compared to achiral samples. When implemented in a high‐throughput format, this technology should greatly facilitate the discovery of asymmetric catalysts in the same way as conventional high‐throughput screening assays.

show abstract

“…The technique has also been reported for prediction of waste water treatment (Hamed et al, 2004). The technique is also found useful in Chemistry, especially for the molecular classification and pattern recognitions (Burns & Whitesides, 1993).…”

Section: Related Workmentioning

confidence: 99%

Comparing the Performance of Predictive Models Constructed Using the Techniques of Feed - Forword and Generalized Regression Neural Networks

Ajiboye

Arshah

Qin

et al. 2016

IJSECS

View full text Add to dashboard Cite

Artificial Neural Network (ANNs) is an efficient machine learning method that can be used to fits model from data for prediction purposes. It is capable of modelling the class prediction as a nonlinear combination of the inputs. However, a number of factors may affect the accuracy of the model created using this approach. The choice of network type and how the network is optimally configured plays important role in the performance of a predictive model created using neural network techniques. This paper compares the accuracy of two typical neural network techniques used for creating a predictive model. The techniques are feed-forward neural network and the generalized regression networks. The model created using both techniques are evaluated for correctness. The resulting outputs show that, the Generalized Regression Neural Network (GRNN) consistently produces a more accurate result. Findings further show that, the fitting of the network predictive model using the technique of Feed-forward Neural Network (FNN) records error value of 1.086 higher than the generalized regression network.

show abstract

Feed-forward neural networks in chemistry: mathematical systems for classification and pattern recognition

Cited by 173 publications

References 42 publications

Clustering of infrared spectra with Kohonen networks

Clustering of infrared spectra with Kohonen networks

Two Methods for the Determination of Enantiomeric Excess and Concentration of a Chiral Sample with a Single Spectroscopic Measurement

Comparing the Performance of Predictive Models Constructed Using the Techniques of Feed - Forword and Generalized Regression Neural Networks

Contact Info

Product

Resources

About