Training Humans and Machines
It synthesizes cross-disciplinary insights for incremental improvements in learning methods, but does not tackle a specific problem or present new results.
The paper reviews existing methods from psychology, education, statistics, and machine learning that improve learning speed, retention, and generalizability, highlighting common principles for potential novel applications in both human and machine learning.
For many years, researchers in psychology, education, statistics, and machine learning have been developing practical methods to improve learning speed, retention, and generalizability, and this work has been successful. Many of these methods are rooted in common underlying principles that seem to drive learning and overlearning in both humans and machines. I present a review of a small part of this work to point to potentially novel applications in both machine and human learning that may be worth exploring.