8
$\begingroup$

This question appears to be off-topic because EITHER is not about statistics, machine learning, data analysis, data mining, or data visualization, OR it focuses on programming, debugging, or performing routine operations within a statistical computing platform. If the latter, you could try the support links we maintain.

This states that we are supposed to ask questions related to statistics, machine learning, data analysis, data mining, or data visualization.

Are we supposed to ask questions related to deep learning/AI?

| |
$\endgroup$
19
$\begingroup$

Deep learning is a subtopic within machine learning, which is on topic. Deep learning is just, um, deeper than regular machine learning. Note that we have an active tag, , that pertains to deep learning with 89 threads. We have also had tags for [deep-learning] and [deep-rl] that are now mapped to and . That doesn't mean that those topics became off limits, just that, e.g., deep learning is now nearly synonymous with neural networks and it isn't useful for us to maintain distinct tags from the perspective of organizing the information on the site. I also find 631 questions with "deep" in the title, of which 90% are not closed.

Artificial intelligence is somewhat trickier. We do have an tag that hosts 229 threads. However, AI is a broader topic than machine learning, rather than a subset. There are aspects of AI that would not fall within our scope. In addition, there is an artificial intelligence SE site, where such questions (even the broader ones) can be asked and might find a better audience.

| |
$\endgroup$
  • $\begingroup$ Great answer. I think the reason it's called deep learning rather than deep architectures is because it's easy to build a deep architecture. The hard part is learning the parameters! I think in the long run, the deep-learning tag shouldn't be mapped to neural networks, but it's true that deep neural networks are an example of a deep architecture. $\endgroup$ – Neil G Jun 17 at 2:17
  • $\begingroup$ @NeilG, there was a question last year about making [deep-learning] a synonym of [neural-networks]. The consensus was yes & it happened. The tags haven't been merged, so the synonym can be undone, but there was a big discussion & the result was fairly clear. $\endgroup$ – gung - Reinstate Monica Jun 22 at 15:20

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .