J
J.D. Wichard
Researcher at AGH University of Science and Technology
Publications - 9
Citations - 145
J.D. Wichard is an academic researcher from AGH University of Science and Technology. The author has contributed to research in topics: Artificial neural network & Ensemble forecasting. The author has an hindex of 5, co-authored 9 publications receiving 142 citations.
Papers
More filters
Proceedings ArticleDOI
Time series prediction with ensemble models
J.D. Wichard,Maciej Ogorzalek +1 more
TL;DR: This work describes the use of ensemble methods to build proper models for time series prediction by using several different model architectures and suggests an iterated prediction procedure to select the final ensemble members.
Journal ArticleDOI
Time series prediction with ensemble models applied to the CATS benchmark
J.D. Wichard,Maciej Ogorzalek +1 more
TL;DR: This work describes the use of ensemble methods to build models for time series prediction by using several different model architectures and suggests an iterated prediction procedure to select the final ensemble members.
Journal ArticleDOI
Detecting correlation in stock market
TL;DR: In order to find hidden correlations in the daily returns, this work builds cross prediction models and uses the normalized modeling error as a generalized correlation measure that extends the concept of the classical correlation matrix.
Proceedings Article
Stochastic Gradient Descent Training of Ensembles of DT-CNN Classifiers for Digit Recognition
Christian Merkwirth,Maciej Ogorzalek,J.D. Wichard,Zbigniew Galias,Bartlomiej Garda,Bartłomiej Kadeja +5 more
TL;DR: This work shows how to train Discrete Time Cellular Neural Networks (DT-CNN) successfully by backpropagation to perform pattern recognition on a data set of handwritten digits and can outperform Support Vector Machines (SVM) on this problem.
Proceedings ArticleDOI
A software toolbox for constructing ensembles of heterogenous linear and nonlinear models
TL;DR: A software toolbox for building ensembles of computer models based on measured time series using statistical learning techniques for training of individual linear and nonlinear models as well as the construction of ensembled of heterogenous models types is introduced.