Machine learning is the process of developing mathematical tools to help computers learn from data. Researchers at the University-Madison are taking that a step further by developing machineteaching.
“My hope is that machine teaching has an impact on the educational world,” said Jerry Zhu, an associate professor of computer science who is leading the project. “It’s quite different from how people usually think about education. It will give us optimal, personalized lessons for real human students.”
Machine teaching would provide instructors with the tools to develop the perfect personalized lesson plan. For instance, the tool could be used to identify the smallest number of exercises needed for a student to understand a particular concept.
“In order for the machine-teaching approach to work, it needs a good model of how the learner behaves—that is, how the learner’s behavior changes with different kinds of learning or practice experiences,” said Timothy Rogers, professor of cognitive psychology at UW-Madison. “Also, the model needs to be computational; it has to be able to make concrete, quantitative predictions about the learner’s behavior.”
Currently, a grant from the UW-Madison graduate school is funding the work. The team plans to seek outside funding sources going forward.