C
Christian Merkwirth
Researcher at Max Planck Society
Publications - 28
Citations - 585
Christian Merkwirth is an academic researcher from Max Planck Society. The author has contributed to research in topics: Artificial neural network & Cellular neural network. The author has an hindex of 12, co-authored 28 publications receiving 533 citations. Previous affiliations of Christian Merkwirth include University of Göttingen & Jagiellonian University.
Papers
More filters
Journal ArticleDOI
Prediction of spatiotemporal time series based on reconstructed local states
TL;DR: Spatiotemporal time series are analyzed and predicted using reconstructed local states using a Kuramoto-Sivashinsky equation and a coupled map lattice predicted from previously sampled data.
Journal ArticleDOI
Automatic generation of complementary descriptors with molecular graph networks
TL;DR: A method for the automatic generation of weakly correlated descriptors for molecular data sets, which can be regarded as a statistical learning procedure that turns the molecular graph, representing the 2D formula of the compound, into an adaptive whole molecule composite descriptor.
Journal ArticleDOI
Ensemble methods for classification in cheminformatics.
Christian Merkwirth,Harald Mauser,Tanja Schulz-Gasch,Olivier Roche,Martin Stahl,Thomas Lengauer +5 more
TL;DR: The application of ensemble methods to binary classification problems on two pharmaceutical compound data sets is described, and several variants of single and ensembles models of k-nearest neighbors classifiers, support vector machines (SVMs), and single ridge regression models are compared.
Journal ArticleDOI
Fast nearest-neighbor searching for nonlinear signal processing
TL;DR: A fast algorithm for exact and approximate nearest-neighbor searching is presented that is suitable for tasks encountered in nonlinear signal processing and compares the running time of the algorithm with those of two previously proposed algorithms.
Journal ArticleDOI
A fully computational model for predicting percutaneous drug absorption.
TL;DR: A new data-driven, predictive model for skin permeability coefficients k(p) based on an ensemble model using k-nearest-neighbor models and ridge regression is proposed, allowing for the reliable, purely computational prediction of skin permeable coefficients.