| Attributs | Valeurs |
|---|
| type
| |
| Is Part Of
| |
| Subject
| |
| Title
| - Structure-Based Predictions of 1H NMR Chemical Shifts Using Feed-ForwardNeural Networks
|
| has manifestation of work
| |
| related by
| |
| Author
| |
| Abstract
| - Feed-forward neural networks were trained for the general prediction of 1H NMR chemical shifts of CHnprotons in organic compounds in CDCl3. The training set consisted of 744 1H NMR chemical shifts from120 molecular structures. The method was optimized in terms of selected proton descriptors (selection ofvariables), the number of hidden neurons, and integration of different networks in ensembles. Predictionswere obtained for an independent test set of 952 cases with a mean average error of 0.29 ppm (0.20 ppmfor 90% of the cases). The results were significantly better than those obtained with counterpropagationneural networks.
|
| article type
| |
| is part of this journal
| |
