Moritz Grosse-Wentrup

Machine learning for neural decoding

The Neuroinformatics lab (IST, Vienna, Austria) develops machine learning methods to decode neuronal states and relate these to cognitive processes.

Understanding the brain means to solve the problem how neural activity gives rise to cognition. This is a causal question that can not be sufficiently answered by correlational methods only. The research group Neuroinformatics develops statistical models and machine learning methods that infer causal relations from purely observational data. We then use these methods to study how neural processes, e.g., as observed by calcium imaging, EEG, ECoG, or fMRI, generate cognition and behavior.

Credit: C. Wyart.

Publications

  • Publication 1: M. Grosse-Wentrup, D. Janzing, M. Siegel, and B. Schölkopf. Identification of causal relations in neuroimaging data with latent confounders: An instrumental variable approach. NeuroImage, 125:825–833, 2016

  • Publication 2: S. Weichwald, T. Meyer, O. Özdenizci, B. Schölkopf, T. Ball, and M. Grosse-Wentrup. Causal interpretation rules for encoding and decoding models in neuroimaging. NeuroImage, 110:48–59, 2015

  • Publication 3: V. Jayaram, M. Alamgir, Y. Altun, B. Schölkopf, and M. Grosse-Wentrup. Transfer learning in brain-computer interfaces. IEEE Computational Intelligence Magazine, 11(1):20–31, 2016

Contact

RG Neuroinformatics, Horlgasse 6, TOP9, 1090 Wien, Austria

Email: moritz.grosse-wentrup@univie.ac.at

Website: https://ni.cs.univie.ac.at/