Generalization

“If you just sort of mix together distribution A, B, and C, there's no guarantee of generalization. What you want to hope to see from these systems is the inclusion of this other data set is improving performance on the other data sets.”

“There's no such thing as generalization. There's just bringing the test distribution into train.”

“The biggest challenge in robotics so far hasn't really been Agility or dexterity, what the robots can do. But then generalization.”

“Society has long encouraged specialization over generalization, but the more time I spend in entrepreneurship, the more I believe that becoming well-versed in many things Is more valuable than being an expert in one thing.”