Dr. Merényi focuses on understanding the structure of large, complex, high-dimensional data with neural computational intelligence techniques. She develops theoretical and simulation tools to discover and express relevant details of relationships in complicated data. Her research is motivated by real problems in Earth and planetary science, astronomy, and medicine. Her collaborative applications are in information extraction from remote sensing hyperspectral imagery, resource mapping, discovery, environmental diagnostics on planetary surfaces; generation of brain maps from functional MRI, analysis of clinical data; discovery from 21st century astronomical “big data”.
WEBSITE(S)| Dr. Merényi's website
Research Areas
Neural machine learning (Artificial Neural Networks); large, high-dimensional, complex data; manifold learning, self-organized learning, clustering and classification, pattern recognition; variable selection, data mining and visualization.
Industry Impact & Relevance
Automatic multi-class target recognition in highly cluttered background; Image classification with reduced set of training labels
Education
Ph.D. Computational Science, Szeged (Attila József) University, Hungary
M.Sc. Mathematics, Szeged (Attila József) University, Hungary
Advisory Role
Ph.D. and Postdoctoral mentor
Senior Fellow, Rice University Academy of Fellows
College Faculty Associate
Teaching Areas
Neural Machine Learning
Regression and Linear Models
Probability and Random Processes
Hyperspectral Image Analysis
Societies & Organizations
Institute of Electrical and Electronics Engineers (IEEE)
Neural Network Society (INNS)
International Astronomical Union
American Society For Photogrammetry and Remote Sensing
Division of Planetary Science, American Astronomical Society