This website is created to provide an overview of Machine Teaching research. Machine Teaching is an emerging sub-field of AI, with connections to diverse applications in the 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. The links below serve as a good starting point to get more familiar with the research:
- Machine Teaching workshop at NeurIPS 2017 conference.
- Introductory tutorial on Machine Teaching research.
- Overview article on Machine Teaching research.
- Seminar course covering topics on Machine Teaching research.
- Lectures on Machine Teaching at Cornell-Maryland-MaxPlanck pre-doctoral school (CMMRS 2019). [Day#1] [Day#2] [Day#3]
For any questions, please contact Adish Singla.