Downloads

Here we offer papers and software for download.

Note that, since this blog is hosted for free by WordPress, it is not possible to provide zip or rar archives for download right here. The archives for software are hosted on Google code instead, links are provided.

Software

NooLabGlue

NooLabGlue is a framework (yet another one) to link applications or parts of applications. The paradigm is aligned to natural neural systems. (…more)

NooLabGlueStarter

The GlueStarter is a small infrastructure component that allows for remote start and shutdown of java jar files. The GlueStarter is a helper component for the NooLabGlue system. In the context of the probabilistic approach to (a population of) growing networks, the GlueStarter can be conceived as something like a “growth mechanism.” (…more)

NooLabFluidSom

The  FluidSom is a Self-Organizing Map (SOM)that is established on a quasi-crystalline fluid of particles. This overcomes the limitations of fixed grid topologies (4n or 6n). Thus, the FluidSom allows for  “natural” growth or differentiation of the SOM-layer, quite in contrast to fixed grid SOM. Their inability to differentiate also renders structural learning impossible for them, hence traditional SOM can’t learn “truly” at all. (…more)

B’Coat

The B’Coat library is still hosted here, kind of left over of my previous engagement. The B’Coat library is a framework that is helpful to create behavior far beyond the stimulus-response-scheme that is so abundant (not only) in the community of programmers and software engineers. Using B’Coat you can link any kind of input to an engine that produces a probabilistic, though deeply structured behavior. It is based on Markov chains and SOMs, programming language is Java.

NooLabCord

NooLabCord is a small and very simple library that helps to leverage and to organize simple (!) multi-threading in a standardized and simple way, hence the name (many threads=1 cord).

The main target of NooLabCord are large lists, or lists which take a long time to work through. In any programming project there are such lists, from image processing, natural language programming, and of course, also in machine-learning. This library provides a simple class that renders the digestion of such lists to a painless routine task. Actually, you just create the object and provide a pointer to your collection or your array. There is almost no overhead in the class, which is a major difference to more elaborate libraries.

A typical i5 or i7 runs on 8 cores, so any kind of list processing could be 7-10 times faster. The library is written in Java.

Documents

.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: