Jump to content
  • Advertisement


  • Content Count

  • Joined

  • Last visited

Community Reputation

151 Neutral

About Vlion

  • Rank
    Advanced Member

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

  1. Vlion

    Creating A Conscious entity

    Oook. A Big Iron AI. For your information, this kind of project is roughly being done. There is a project that is attempting to gain the sum of human knowledge. I forget the link, it's been a year since I saw the project. But the idea is people online are asked to put in a piece of common sense data and the logic engine tries to make a connection. I'm looking into NLP right now, in preparation for doing a Master's in it, so I feel comfortable contributing here. I'm also taking a senior-level AI course. What I know about big AI: the theory really isn't there. We can't do much in terms of a simple document analysis. How are you going to handle non-domain specific topics? Now, here's my idea. Create a "baby". Much research has gone into making adult AIs. Has someone started with a "blank slate" and attempted to train elementary facts into a neural net? Why are neural nets considered better than logic engines? Because they are i)nat-cher-al, and ii)they are a great way to represent fuzzy logic engines. They also are very simple, unlike logic structures. Of course training non-trivial neural nets is fairly difficult. (I did research last summer with respect to recurrent classical neural nets) Let me ask you guys this question: Situation: Hospital where a man has just died. He has enough chemicals and poky things in him that the body will not deteriorate, but his heart just gave out after that last McFat burger. It is evident that Mind Has Left The House. Why won't he come alive if a doctor puts a fake heart in? This is the reverse question, really. What is death, and how do we go from death to life?
  2. Depends upon your neural model. You could have a thread running through the neurons firing them like mad, and then another polling neurons waiting for the impulse to sum to be over the threshold, and then they fire. As an example, you realize. ^_^ Classically, a network attempts to fire in layers, I believe.
  3. Depends on where you want to go. For straight-up syntax parsing, Prolog is a good way for a fast attack. For more complex parsing, the lex/yacc pair is a good one. Since eventually you will hit the CFG limit with those, you will need to have some way to parse CSGs; and that means you probably will have to write your own. Here Lisp or C++ would work well. Some people use Perl for their NLP work. My point is your original question isn't that good. You can use most any modern programming language for most anything. What are you going to do? Now select the language that gives the easiest path through that problem for you.
  4. Vlion

    Recurrent Neural Networks

    Stochastic algorithms can be used to train RNN decently well. Particle swarm optimizers and genetic algorithms have been used, to my personal knowedge.
  5. *pulls up graph theory book* I'm going to recommend doing some searches on CiteSeer for "cutvertecies" and "bridges". Essentialy, you are trying to not remove them in the random removal process, if I understand you correctly. So you will have to enumerate all bridges and all cutvertecies, and remove them from the set of delete-able vertecies. Insofar as I know, these types of problems are NP-hard or NP-complete, so you can expect huge amounts of time for solving them.
  6. Vlion

    STL vectors mobo jumbo!

    vector<vector<uint> > array; How this works is: You have a containing array of type vector<vector<uint> >. This needs to be initialized to the number of columns. So you will have to push back some empty vector<uint> into that holder array. These will "hang" off of the holder. These now can get data pushed back into them. You get what I'm saying? Post more of the code next time, and it will go easier for us who answer questions. :)
  7. Vlion

    Tutorials - C++ or high language

    Expect 2 years in C++ to get the language, plus the finer points. In the second year, study data structures, first linear ones like "lists" or "queues", then non-linear ones like "trees" or "graphs". Somewhere while you work through advanced C++ and beginning data structures, you should study Assembly lanaguages. While not commonly used in program development, it brings a low-level understanding of how the computer works. You already know this, yes? After the second year, find a totally different language in a different paradigm. C++C#/Java/Basic/Pascal/Delphi/Assembler are all the same general idea or paradigm- understand one, understand them all. For the alternate paradigm, Scheme/Lisp or Prolog are the best ones really. This will allow you to have an understanding of alternate ways to consider ideas. By this time, you should be able to spend 3 months and have a good grasp of a new programming language. I don't know how things work in Norway, but at that point you would have roughly the practical knowledge of a junior in computer science, in the US. At that point, your basic programming knowledge will be finished. You can basically branch out where you want- software engineering, theoretical computer science, etc. You seek tutorials. Unfortunatly, there tends to be two classes of knowledge online. Really basic, and really advanced. I canna help you very much here. SGI has a great reference for C++'s standard library. If you want free programs, install Debian Linux on a computer. You can get almost any standard programming language on it, ranging from C++ to Haskell to Lisp to what-have-you. And finally, I do not recommend a Microsoft-only language at all. Learn something that can be used on multiple operating systems. Good luck.
  8. Vlion

    Suggest a language...

    Java, probably. It has the cross-platform VM and windowing libs. Same reason for C#, but C# is newer and less completly supported. Or you could write rockin' C++ code and modularize the OS-specific code out. *shrug* I'd say Java, honestly.
  9. Vlion

    Need idea for a 4th grade sci project

    A minimal calculator in QBasic? Or perhaps a program in LOGO? Try and figure out AND/OR/NOT circuits using water perhaps? (See pattern in the stone book for the idea)
  10. Vlion

    Not Good

    Well, what is really not good is your lack of a descriptive title. ^_^ This isn't really a good site to ask that class of question on either. Its a game programming oriented site. Now, what I would recommend in your situation is perhaps the hardest thing: practice. Sit down and start working math problems. Dig up a old high school algebra 1 textbook(50s-70s ones are best), and work through the examples. Keep doing that with a single type of problem until you understand what problems translate to that class and how to manipulate them into a solution. Program the problem in and manipulate the numbers with the computer until you get an intuitive feel for it. Be fore-warned, though. There is a lot in algebra thats not explained well or in full until calculus and discrete mathmatics. So you'll have to stick it through. Good luck!
  11. Vlion

    Question about genetic algorithms

    Look up academic papers by Terry Soule if you are concerned with the if(false && false) type bloat. He studies that stuff- phd dissertation, etc. Look for it on Citeseer. The main problem I have with genetic tecniques is that it is (a) solution, not the solution, nor the solution within $epsilon of accuracy. This becomes important when you are working with functions you have no idea of how they are minima-, optima- continuousness-wise. But yeah. Look for GECCO papers- its a big GA/GP conference.
  12. er, what you are doing is called "Change of Basis" technically. Examine it, then come back to this thread, and all should be made clear. :)
  13. Vlion

    Do these words exist?

    Well...being nit-picky, a prefix(noun) on a word is the starting ordered sequence of characters, of n length, not including the last. to prefix(verb) is to put something on the front of. And vice versa. Nit-picking, I know, but ^_^.
  14. 1) You'd want to transform your net and/or input so that it could handle missing points. 2) Stateful neural nets are known as feed-back nets. They are using for voice recognition, among other things. Genetic algorithms are often used to train them.
  15. Vlion

    Math help.

    Start manipulating, using the rules of algebra. When you begin to understand how they affect the expression, start moving the equation into the required form.
  • Advertisement

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

GameDev.net is your game development community. Create an account for your GameDev Portfolio and participate in the largest developer community in the games industry.

Sign me up!