It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.
Closed 11 years ago.
Has anyone tried to implement Numenta's most recent cortical learning theory (http://www.numenta.com)? I'm working on it and would like to share experience.
I think the ideas from Numeta are very promising. But as with any company that wants to make money they are not verbose enough about the technology so that one should be able to re-implement their system (at least from what I have seen so far). It is probably not in their interest that one could just rebuild the system from which they plan to make money.
Also their system is very general and complex. So unless you have a lot of experience with other kinds of neural networks and learning algorithms, I would not recommend experimenting with their ideas. First try to do Backpropagation and maybe some of the less advanced temporal learning until you are really familiar with that.
Related
It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.
Closed 10 years ago.
I was wondering if folks use VHDL/FPGAs in scientific computing.
An example scenario that I was thinking off was say:
Construct an arbitrary precision floating point adder
Configure an FPGA board to then add such numbers
So I was looking for references (example code) where VHDL/FPGAs have been used in scientific computing.
Thanks in advance.
There are several vendors who build heterogeneous computing systems using FPGAs. I doubt you'll find complete source code for such systems.
SRC Computing
Convey Computer
Mitrionics. A reseller of other systems.
Novo-G. An academic project.
Look into radio astronomy. With arrays such as the VLA and ALMA, the massively parallel correlator is the part that could be considered most important. These typically use FPGAs but could use custom-designed chips for extreme performance at higher cost.
Some fine reading:
https://science.nrao.edu/facilities/cdl/digital-signal-processing
http://web.njit.edu/~gary/728/Lecture8.html
It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.
Closed 10 years ago.
I have a question. Gradually quantum computers will emerge someday. So, nowadays making algorithm efficient is important; I mean, making it optimal to run as fast as possible. But once quantum PC emerges does the algorithm performance improvements are still important?
Cheers
Quantum algorithms have the possibility of searching a complete number space for an answer in one go, that much is true. However, the algorithm you choose will still determine how many of these steps are needed, and whether you can pack the whole space with useful inputs.
I think its too early to worry about it. It also might be quantum computer will never made.
It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.
Closed 10 years ago.
Im searching for numerical algorithm realization for nonlinear equations system solver on PHP, C, C++, Java (with readable code :). Where I can find them?
Thx.
Look in Numerical Recipes -- the latest edition has reasonable C++ code. Even if they don't have code to exactly solve your specific application, there's a good chance they have something you can use.
It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.
Closed 11 years ago.
I want to know if is there any specific algorithm that can be followed to understand the meaning of a word/sentence/paragraph. Basically, I want to write a program that will take text/paragraph as input and try to find out what its meaning is. And thereby highlight the emotions within the text.
Also, if there is an algorithm to understand things, can the same algorithm be applied to itself? It reduces the quest further to a point where we become interested in knowing meaning of meaning OR rather definition of definition.
You want Natural Language Processing and Semantic Technology. This is still a flourishing area in computer science. Look at things such as a Semantic Reasoner. You can start with Jena. There are also other things you can look at such as Academic Thesis papers.
It's difficult to tell what is being asked here. This question is ambiguous, vague, incomplete, overly broad, or rhetorical and cannot be reasonably answered in its current form. For help clarifying this question so that it can be reopened, visit the help center.
Closed 12 years ago.
just now I teach someone ruby and I need to give simple program (1-3 classes) to write. Could you give me an example of such program? Or some web resources? It should not be complicated it self, rather it should show ruby (is awesome ;)
Check out http://ruby4kids.com/
Chris Pine's Learn to Program is available online and uses Ruby as its language. It's geared towards novice programers and should contain easy examples. At the end of various chapters you'll also find sections called "A Few Things to Try", which contain nice exercise suggestions.
I found http://rubykoans.com/, and its quite great :)