23

Besides the questions on our site, there's already Computer science, Artificial Intelligence and Data Science (all of which have questions on neural networks - and that's not even counting the neural networks questions on StackOverflow and on Theoretical Computer Science ...). I'm not sure that adding a fifth (or seventh ...) site fielding questions on the ...


18

Questions about the machine learning algorithms (as long as they're actually about the algorithms and not about specific implementations) are clearly on topic here. In this case the fact that the data is coming from vision will probably be relevant, but may not be central to the question. Questions about what image manipulations make sense to perform are ...


15

This is a subtle issue, and I think you have it right, but it will always be tricky in practice. My own guideline for what is on-topic is (conceptually) straightforward: What does the OP need explained? If what they don't know / misunderstand is something about how the code works (e.g., in that language), then this is ultimately a programming question and ...


14

Reinforcement learning is on-topic here, and I hope our ML side grows as much as possible, so I hope you will ask it here. However, you should consider the nature of the RL topic about which you want to ask. For example, if you wanted to ask about the mathematical analysis of various (asymptotics and such), you may prefer to ask on math.SE, etc.


13

There used to be this Stack Exchange proposal: Image Processing and Computer Vision. But it got closed: [image-processing] is the #1 tag on our Signal Processing site. After 11 months in development, the Community Team has reviewed this proposal and concluded that we should not try to split this subject off into another site. – Robert Cartaino♦ Apr 6 at ...


12

This is not just an issue with ML code, it's an issue with any code that doesn't do what the OP wanted that's posted to the site at all. It could either be a problem of understanding what the algorithm is (not really knowing the correct thing to code to achieve the aim) or it could be a problem of converting a correct algorithm into code (implementation). ...


11

Machine learning is on-topic here at Cross Validated—see What topics can I ask about here?, What is on topic on Cross Validated?, Are the “Machine Learning” questions on topic?, & Is machine learning a part of statistical analysis? & Should Machine Learning SE be merged with CrossValidated?. That doesn't seem to have ever been contested. (It's ...


9

It says so on StackOverflow, so it must be true!


9

Should a “Neural Network” Stackexchange site be created? This question has been answered by the response on Area51: Artificial Intelligence - closed after 18 days in beta 4 years ago Artificial Intelligence - closed after 12 days in beta 7 years ago Artificial Intelligence - 665 days in beta (Third time's a charm) - Almost 650 "Neural" tagged Machine ...


8

First of all, as already said in @gung's comment, CrossValidated is the site to ask questions on machine learning. Many machine learning questions (mostly those that focus on coding issues) are also asked and answered on Stack Overflow. Moreover, if you search Area51, you'll see that there were already two proposals for "Machine Learning" sites, but they ...


8

Just containing code doesn't make it off topic; the question seems to me to be firmly on-topic. In any case, in relation to programming questions (which I don't think this one actually is), the help/on-topic says: if it needs statistical expertise to understand or answer, ask it here So even if it were more of a programming-related question than it ...


7

Neither StackOverflow.com nor CrossValidated.com hires anyone to answer the questions. Both sites rely solely on volunteers. You could ask StackExchange.com why they do not pay people for answering questions, but the likely answer would be that this would be a bad business model (how would they profit from it?). Moreover, I'm afraid that the kind of people ...


6

If your only question / planned answer for the thread is "here is the code to upload a text file to h2o from your interface", then the question will be fine on Stack Overflow. On the other hand, if you want to talk about "the evaluation of data", that is on-topic here, even if code is appended. There is certainly nothing wrong with having code (R, SAS, ...


5

Methodological questions concerning crowdsourcing and machine learning are on-topic on Cross Validated SE, but they can't be: duplicate unclear. too broad. primarily opinion-based. Questions which ask for references are not off-topic, but depending on how it is asked some users can consider it 'too broad'. So, always try to be the most specific as ...


5

In addition to the other options listed here, I would think computer vision falls within the purview of artificial intelligence. There is now an AI SE site, and I notice that it has a computer-vision tag.


4

Neural networks is simply one method. It is statistic in a sense that the neural network can be thought as a complicated function that is trained to fit the data in a best possible way. As such it is not that academic approach as an engineering thing; things that work are used and people build intuition with experience on the matter. Thus it is hard to say ...


3

I think that Data Science as a field is quickly sliding into obscurity in terms of applied statistics. It's becoming a hybrid of IT and business analytics. The data scientists are not able to answer AI and ML questions anymore, so they increasingly flow into CV. I see a steady stream of AI questions not only incoming, but also being properly answered. We ...


3

Sites which have a computer vision tag might be interesting. The number of quesions asked there is an indicator for how relevant this might be. However, you should also consider that some sites (like StackOverflow) are much bigger than others (like datascience, which might be a good fit for you). StackOverflow: 5665 questions (I guess mainly about ...


Only top voted, non community-wiki answers of a minimum length are eligible