The group's research interests are in the algorithmic foundations of machine teaching, and applying these algorithms in the application domains of computational education and trustworthy AI. Formally, machine teaching is an inverse problem of machine learning: it involves a teacher with a desired goal, and the teacher's objective is to find an optimal training sequence to steer a student/learner towards this goal. For instance, in an educational setting, the teacher (e.g., a tutoring system) has an educational goal that she wants to communicate to a student via a set of demonstrations; in adversarial attacks known as training-set poisoning, the teacher (e.g., a hacking algorithm) manipulates the behavior of a machine learning system by maliciously modifying the training data. Machine teaching is an emerging sub-field of AI, and the group plans to advance the research on machine teaching via (a) developing new models, algorithms, and theory of machine teaching; (b) applying these algorithms to real-world applications by building and deploying new services. The following two websites serve as good starting points to get more familiar with the above-mentioned research interests: (i) https://teaching-machines.cc/ and (ii) https://rl4ed.org/.
- 01.10.2021: Five papers accepted at NeurIPS'21.
- 01.10.2021: We are co-organizing the workshop RL4ED - Reinforcement Learning for Education as part of the AAAI'22 conference.
- 01.10.2021: We are teaching a course on Reinforcement Learning.
- 01.10.2021: We are teaching a seminar course on Adversarial Reinforcement Learning.
- 25.04.2021: We are co-organizing the workshop RL4ED - Reinforcement Learning for Education as part of the EDM'21 conference.
- 25.04.2021: We are co-organizing the workshop Human-AI Collaboration in Sequential Decision-Making as part of the ICML'21 conference.
- 15.04.2021: We are teaching a seminar course on Reinforcement Learning for Education.
- 10.04.2021: Papers accepted at AAAI'21, AISTATS'21, and EDM'21.
- 01.11.2020: We are teaching a seminar course on Multi-agent Reinforcement Learning.
- 25.09.2020: Two papers accepted at NeurIPS'20.
- 05.06.2020: Two papers accepted at ICML'20.
- 05.06.2020: Papers accepted at IJCAI'20, AAMAS'20, and EDM'20.
- 01.05.2020: We are teaching a seminar course on Machine Learning and Formal Methods.
- 01.01.2020: We have postdoctoral and Ph.D. positions available in various topics including (i) AI for education and intelligent tutoring systems, (ii) machine learning applied to program synthesis and formal methods, (iii) multi-agent reinforcement learning, and (iv) adversarial machine learning.
- 01.01.2020: We are looking for motivated students for internships and M.Sc. thesis projects.
- 03.09.2019: Three papers accepted at NeurIPS'19.
- 10.05.2019: New Ph.D. position as part of a joint project between Microsoft Research Cambridge and MPI-SWS: Reinforcement Learning for Enabling Next Generation Human-Machine Partnerships.
- 09.05.2019: Two papers accepted at ICML'19 and one paper accepted at IJCAI'19.
- 06.09.2018: Three papers accepted at NeurIPS'18.
- 10.11.2017: Three papers accepted at AAAI'18.
- 09.12.2017: We gave a tutorial on Introduction to Machine Teaching at the Workshop on Teaching Machines, Robots, and Humans, NIPS 2017.
- 10.10.2017: We are co-organizing the NIPS'17 Workshop on Teaching at Long Beach on 9 Dec, 2017.
|Imprint / Data Protection|