For Teaching Perceptual Fluency, Machines Beat Human Experts
- Ayon Sen, Computer Sciences Department, University of Wisconsin-Madison, Madison, Wisconsin, United States
- Purav Patel, Educational Psychology, University of Wisconsin - Madison, Madison, Wisconsin, United States
- Martina Rau, University of Wisconsin - Madison, Madison, Wisconsin, United States
- Blake Mason, Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, Wisconsin, United States
- Robert Nowak, Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, Wisconsin, United States
- Timothy Rogers, UW-Madison, Madison, Wisconsin, United States
- Jerry Zhu, Computer Sciences, University of Wisconsin-Madison, Madison, Wisconsin, United States
AbstractIn STEM domains, students are expected to acquire domain knowledge from visual representations that they may not yet be able to interpret. Such learning requires perceptual fluency, or the ability to intuitively and rapidly see the underlying concepts in visuals and to translate between them. Perceptual fluency is acquired via nonverbal, implicit learning processes. Thus far, we have lacked a principled approach for identifying a sequence of perceptual fluency problems that promote robust learning. Here, we describe how a novel machine learning technique can generate an optimal sequence of perceptual fluency problems. In a human experiment, we show that a machine-generated sequence outperforms both a random sequence and a sequence generated by a human domain expert. Interestingly, the machine-generated sequence resulted in significantly lower accuracy during training, but higher posttest accuracy. This suggests that the machine-generated sequence induced desirable difficulties. To our knowledge, our study is the first to show that machine learning can yield desirable difficulties for perceptual learning.