Methods for measuring and generation of whitebox models of human behavior
Subprojects:
- Subproject SP1.1: Optimization of behavioral experiments with AI
Lead: Frank Jäkel, Tom Wallis - EEG and NIRS experiments (EEG/NIRS support) for project areas 1 and 3
Lead: Ralf Galuske - Subproject SP1.2: Inverse Reinforcement Learning explains human behavior
Lead: Jan Peters - Subproject SP1.N: Development of new methods for investigating human problem-solving behavior
Lead: Constantin Rothkopf, Frank Jäkel
Methods to analyze blackbox models in machine learning
Subprojects:
- Subproject SP2.1: Probabilistic models of and with deep neural nets
Lead: Angela Yu, Stefan Roth - Subproject SP2.2: Inverse Reinforcement Learning explains machine behavior
Lead: Constantin Rothkopf, Heinz Koeppl - Subproject SP2.3: Hybrid models: deep and probabilistic, graphical models interact mutually
Lead: Constantin Rothkopf
Transparent cooperation between human and machine using whitebox models for both
Subprojects:
- Subproject SP3.1: Human and machine walking together
Lead: André Seyfarth - Subproject SP3.2: Humans and machines learning together
Lead: Kristian Kersting - Subproject SP3.3: Human trust in self-explaining AI
Lead: Ruth Stock-Homburg - Subproject SP3.N: Using human behavior for automated explanations
Lead: Frank Jäkel, Constantin Rothkopf
