This post seems to over-exaggerate a commonly known mathematical property.
Suppose I have languages X, Y, and Z. My machine currently knows how to translate between X->Y and X->Z. The goal is to turn Y into Z without direct training. The process would be to translate Y into X and X into Z.. effectively Y->Z.
This isn't really transfer learning as much as it is logical induction...Or am I missing something?
Suppose I have languages X, Y, and Z. My machine currently knows how to translate between X->Y and X->Z. The goal is to turn Y into Z without direct training. The process would be to translate Y into X and X into Z.. effectively Y->Z.
This isn't really transfer learning as much as it is logical induction...Or am I missing something?