Communications of the ACM
Great Innovative Idea: Machine Teaching
University of Wisconsin-Madison associate professor Xiaojin Zhu says machine teaching is about finding the optimal (smallest) training set.
Credit: Meghan Kelly/VentureBeat
Machine teaching is an innovative idea from University of Wisconsin-Madison associate professor Xiaojin Zhu whose paper, "Machine Teaching: An Inverse Problem to Machine Learning and an Approach Toward Optimal Education," won the Computing Community Consortium-sponsored Blue Sky Ideas Conference Track series at the Association for the Advancement of Artificial Intelligence's Conference on Artificial Intelligence in January.
Zhu describes machine teaching as machine learning turned upside down. He says machine teaching is about finding the optimal--the smallest--training set, and it mathematically formalizes this idea and generalizes it to many kinds of learning algorithms and teaching targets.
Zhu says machine teaching can have an impact on education, where the student is really a human student and the teacher has a target model (the education goal). "If we are willing to assume a cognitive-learning model for the student, we can use machine teaching to reverse-engineer the optimal training data--which will be the optimal, personalized lesson for that student," Zhu says.
From CCC Blog
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA
No entries found