How can we better understand what’s going on inside the “black box” of machine learning algorithms? In episode 53, Been Kim from Google Brain talks with us about her research into creating algorithms that can explain why they make the recommendations they do via concepts that are relatable by their users.
Analysis of 90,000 responses to Big Five questionnaires draws the universality of these personality traits into question, especially among those in developing countries.
Debt cancellation for borrowers who were in default on their student loans found to result in more rapid development of other outstanding debt and a subsequent increase in average income.
In a step toward molecular storage systems that could hold vast amounts of data in tiny spaces, researchers develop proof of concept showing that it’s possible to store image files in solutions of common biological small molecules.
