Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 3 years ago.
Improve this question
I have a data set with 2400 samples and 10,000 features. All the data is binary (+1 or -1). I need to run it past an SVM algorithm so I could compare my algorithm to it. However, I know not much about SVMs or which package to use. I tried reading about to so I could implement one, but it's way over my head, and I need to get from it is the weights vector. I'm a windows user and I've got my implementation in Java. I could export my data into a text file with 1s and 0s. I have access to MatLab, but something tells me it will be extremely slow and won't really run on my 1.6ghz 2gb RAM laptop (and I need it to) fast enough. I have to run the algorithm a couple hundred times to get accurate results.
I'm really just looking for a quick and easy to understand library or SVM implementation that I can use in my case.
Thank you all. Feel free to ask any additional questions to assist me better.
I ended up using a JNI for SVN light that can be found here: http://www.mpi-inf.mpg.de/~mtb/svmlight/
Didn't take long to figure out how to use it and it's surprisingly fast (seconds).
I don't think that there is any path to a 'quick and easy understanding of an SVM.' The math is hard and trying to train one without a good understanding is a very quick trip to shooting yourself in the foot.
OpenSVM from sourceforge is certainly sitting there. It shouldn't matter to you if it's in Java, just download a JDK.
I can't answer your question as to the likely performance of a SVM training procedure in MatLab, perhaps someone else can.
Related
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 7 years ago.
Improve this question
I want to write a bot for 500px.com which automatically likes pictures and follows random people. Sadly I don't have a clue where to start, are there any good tutorials or something? I googled, but could't find anything useful really!
I work at 500px. We'd really rather you didn't try to game the system, it hurts the community when you do and isn't fair to other users.
I mean, I'm a developer, I get that this might just be a curiosity thing for you. Maybe you just want to see what you can do. But maybe your efforts would be better spent, say, playing with our REST API.
But if it is that you're just trying to get more exposure, I hope that you'll reconsider your strategy. Focus your efforts instead on contributing meaningful content, engaging with your fellow users, working on your craft. When you game the system, you're advancing yourself on the backs of other photographers. The more people that engage in this sort of behaviour, the harder it becomes to find meaningful content, and over time everyone suffers.
No
Your problem is concept -- you want to write a automatic function that acts as if it is a human entity. This means that even if this is desired by the company behind the http://www.500px.com website, this does come across as something impersonating a valid human user, and as such will need to face and overcome the usual challenges of such thing as filling in online forms, logins and verification methods automatically and reliably without being detected as a 'bot .
This is potentially a very significant undertaking, and not to be underestimated. By posting this question on stack overflow you're pretty much giving away that you've very likely not got the basic skill-sets required for carrying out this task.
If this task is however in partnership or for the company behind the 500px.com website, then you will have access to very specific and first hand information about the details and website code and structure they use.
Both of the above conclusions - to me - imply that you're far below the very-probably required level of knowledge and you're going about finding that knowledge in entirely the wrong way.
Instead, find a programming language of your choice and learn it inside out and upside down, then you'll have (slightly) more chance at doing something like this.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 9 years ago.
Improve this question
We are building a text search solution and want a way to measure precision and recall of the system every time we add new document types. From reading some of the posts here it sounds like a machine learning based solution is the way to go. Can a expert comment on this? We will then look to add machine learning folks to our team.
The only way to get the F1-score require knowledge about the correct class, rank of all samples obtains by evaluation querys, and you also need thoses evaluation querys.
Any machine learning will need a large quantity of manual work to provided thoses samples and/or querys. So large that it wont save you any time.
Another bad aspect of this evaluation is through to learning-related intrinsic errors. It will go with the growing size of the index of the search engine and the number of examples required. You never get a good evaluation.
Forget machine-learning for the evaluation of search engine.
Build by hand your tests querys and sample, by the time it will become big and reliable.
If you really want machine-learning in your system, you should look at query pre-processing. Getting some meta-information about the query by another way (you say SVN, why not?) is generaly a good for performance and while it did'nt change the result, you can use the same sample for an end-to-end evaluation.
That what I have done few years ago, but with naive baye classifier on natural langage analysis.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question appears to be off-topic because it lacks sufficient information to diagnose the problem. Describe your problem in more detail or include a minimal example in the question itself.
Closed 9 years ago.
Improve this question
I would like to implement a temporal tagger of my own just for my experience. I just want to know how hard is it to implement a good temporal tagging system by myself (only me) and what kind of an approach should I take.
Thanks.
Try to replicate recent work by Angeli, Manning, and Jurafsky in NAACL 2012, "Parsing Time: Learning to Interpret Time Expressions" and see where you get.
http://scholar.google.com/scholar?hl=en&q=angeli+manning+jurafsky+parsing+time&btnG=&as_sdt=1%2C33&as_sdtp=
Short of wasting a ton of time writing regular expressions every which way 'til Sunday (and still probably not covering expressions like "'til Sunday"), that's probably the best anybody has done. If you're going to go the regexp route, at least try improving something like Ruby's date module or some other free software date/time parser, so others can benefit from your work, and so you don't have to reinvent every wheel.
I'd love to hear about where you take this, if you actually do work on it.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I am in the process of choosing project for uni. And I am really interested on combining genetic algorithms and computer security.
Therefore my question, Is it possible to use GA on any aspect for computer security? For example?. I was thinking something like a evolutionary firewall/anti-virus that will be able to self protect/inhibit threats. Is such thing plausible?
I really appreciate you guys input, advice, comments.
First of all, the whole idea of genetic algorithms is still being debated, i.e. if genetic algorithms are in any way better suited to solving optimization problems than other methods (who are either proven, easier to use, or provide other advantages).
That being said, yes, I know of a security-related application of genetic algorithms, mainly used in fuzzing to optimize code paths and therefore code coverage. There is a paper called Vulnerability analysis for x86 executables using genetic algorithm and fuzzing and a BlackHat presentation predating that paper by two years called "Sidewinder": An Evolutionary Guidance System for Malicious Input Crafting
I briefly looked into this before, and there seems to be quite a bit of resources around using genetic algorithms for network intrusion detection. Hope it helps.
Take a look at Stephanie Forrest's group's work on computer immune systems.
It's not traditional GAs, but it's very close. Hope that helps.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 5 years ago.
Improve this question
I recently found out about livecoding where someone will program something on the fly to make music. Apparently there are special languages and libraries for this sort of thing. So I'd like to know if anyone has any experience with it and if they have any languages, libraries or tools to suggest.
Check these resources:
SuperCollider (Environment and programming language for real time audio synthesis and algorithmic composition)
ChucK (Strongly-timed, Concurrent, and On-the-fly Audio Programming Language)
TOPLAP (temporary organization for the proliferation of live audio programming)
I want to second the recommendation for Impromptu as well:
Wholesale utilization of your Mac: audio units, camera, openGL...etc (I actually ended up buying a Mac after playing around with this app.)
Very simple and easy to start : The tutorial gets to the fun fast. Perhaps the clumsiest aspect is getting the keybindings installed : (you will need to install in ~/Library/KeyBindings/DefaultKeyBinding.dict)
It uses Scheme(Lisp dialect) a highly iterative language, suitable for prototyping apps one line at a time.
Now there is also Sonic Pi which is a lot of fun.
It is an Open Source live coding environment based on Ruby that runs in a variety of environments including the Raspberry Pi and is build on top of the Supercollider synthesis engine.
Sonic Pi has been designed with the aim to find a harmonious balance between three core principles:
Simple enough for the 10 year old within you
Joyful enough for you to lose yourself through play
Powerful enough for your own expressions
Sample code:
loop do
sample :perc_bell, rate: (rrand 0.125, 1.5)
sleep rrand(0, 2)
end
You should check out RTcmix (Real-time Cmix). I saw a great livecoding demo by one its developers, but I haven't been able to find any videos online.
I've been using RTcmix with its Python front-end module to experiment with algorithmic composition. It's very easy to use and has nice results.
EDIT
I've been investigating livecoding further recently, and RTcmix is not intended for this, but in some cases, it can work. It's much better for pre-processed scores. Sorry for any confusion. :)