Human versus Machine: Better Adaption of Pedagogy to AI than to our KidsAccording to  research from Carnegie Mellon University kids solve math problems by going through four distinct stages: encoding (reading and understanding the problem); planning (working out how to tackle it); solving (crunching the numbers) and responding (typing in the correct answer). This follows the general path that is set out in school, but is not something missing?

Learning to Learn

Jonathan Rochelle, head of the product management team for Google for Education says to Business Insider: “We’re not teaching them how to learn.” Reflection and putting subjects in perspectives and in a general framework are all too often given to little space in school education, while at the same time this is the basic trigger for the ongoing extraordinary development of artificial intelligence. The pedagogic method for machine learning, e.g. IBM Watson, is that it continuously is taking in new information. And then fits it into the frameworks that it was given at birth. This efficiency thereby depends on Watson’s ability to learning to learn. In this spirit for school education the pedagogy must stronger focus on making pupils understand why a particular math equation works and when it’s applicable in the real world, rather than just teaching the formula.”, according to Rochelle.

Improving pedagogy

The lead researcher John Anderson of the study mentioned at the beginning of this story says: “If we can better understand how students are solving problems. We can improve teaching techniques too.” The study includes 80 students that worked with different math problems. While the research team was mapping each brain’s activity with brain scan technique.

Written by
LarsGoran Bostrom©

These are the four stages of your brain on maths

Google’s top education expert says we teach machines better than we teach our kids