New answers tagged

2

These terms don't have a precise meaning. It depends on the company/lab. I know of people who are "data analysts" yet do research in machine learning but also "data scientists" who don't do any research. In fact, machine learning and deep learning are probably the hottest and the most hyped research areas currently. As such, and also ...


0

Traditional single-label classification implies disjoint labels. To the extent that labels are not disjoint or distinct within a single-label classification task, the problem is one of the definition of distinct concepts. This problem has been discussed as early as 1984 in Valiant's "A Theory of the Learnable" where he identified the theoretical ...


1

Usually, when considering machine learning algorithms from a theoretical perspective, we are interested in PAC learnability, or some other learnability definition (most of those are very similar to PAC, since everything in the machine learning region is stochastic). Under those definitions, there are a few possible "metrics" that measure something ...


Top 50 recent answers are included