Free crossover software for linux

Evocosm is a C++ Framework for Evolutionary Computing library.
Evocosm is a set of classes that abstract the fundamental components of an evolutionary algorithm. Ill list the components here with a bit of introduction; you can review the details of the classes by downloading the code archives or by reviewing the online documentation (see the menu at the articles beginning for code and documentation links.)
All class documentation was generated from source code comments using doxygen. These docs have not been thoroughly proofread, so they may contain a few typos and minor errors. Self-publishing has taught me the value of a good proofreader.
Evolutionary algorithms come in a variety of shapes and flavors, but at their core, they all share certain characteristics: populations that reproduce and mutate through a series of generations, producing future generations based on some measure of fitness. An amazing variety of algorithms can be built on that general framework, which leads me to construct a set of core classes as the basis for future applications.
The classes include:
Random Numbers
Evocosm relies on the code in The Twisted Road to to Randomness for random number generation. The Mersenne Twister algorithm is particularly well-suited to evolutionary algorithms, based on its long period, granularity, "randomness", and speed. As of the 2.1.0 release of libevocosm, the mtprng class resides in libcoyote, and not libevocosm as it did earlier. This means that any program using libevocosm must also link against libcoyote.
Validation
To validate function arguments, Evocosm uses the code I describe in Beyond Assert; this code is part of libcoyote. Any program using libevocosm must also link against libcoyote.
Floating- Point Chromosomes
Evcosom supports the crossover and mutation of IEEE-754 floating-point numbers, using an algorithm I invented in the mid-1990s. This topic is covered in detail here.
Roulette Wheels
The roulette_wheel class implements the concept of a "software roulette wheel" for Evocosm. This is a tool for natural selection, wherein the fitness of an organism determines the width of its "slot" on an imaginary roulette wheel.
Organisms
Think of an "organism" as an answer to a problem posed by a fitness landscape; "genes" define its behavior and an associated fitness value is assigned by an evocosm during testing. Evocosm provides the freedom to define organisms as almost anything: bit strings, floating-point numbers, finite state machines, LISP programs, or external robots controlled via radio waves. In A Complexity of Options, I used an Evocosm-derived GA to determine the gcc options that produce the faster code.
Fitness Landscapes
A "fitness landscape" defines the environment where organisms "live" or a problem that they are tested against. The landscape is intimately tied to the nature of the organism; think of an organism as a potential solution to a problem implemented by the landscape. A floating-point organism, for example, could be tested by a fitness landscape that represents a function to be maximized. Or, an organism describing the shape of wing could be tested by a landscape that simulates a wind tunnel.
Evocosms
The evocosm class binds a population of organisms to a set of objects that define the rules of survival and reproduction. An evocosm will have one or more populations, which will evolve against population-unique and shared (common) fitness landscapes; breeding is controlled by a set of class objects from the following classes.
Fitness Scaling
As a population converges on an "answer", the difference between fitness values often becomes very small; this prevents the best solutions from having a significant advantage in reproduction. Fitness scaling solves this problem by adjusting the fitness values to the advantage of the most-fit chromosomes. Evocosm includes a variety of fitness scaling algorithms.
Migration
A migrator removes individuals (via "emigration") from a population of organisms, transferring them to another population (via "immigration"). The only concrete implementation of this interface is random_pool_migrator, which defines a specific number of organisms that may migrate from each population to another. When creating a random_pool_migrator, specify the number of organisms that can migrate from each population. Migration is, of course, meaningless in any application that has only one population.
Selecting Survivors
A selector decides which organisms survive from one generation to the next. Some evolutionary algorithms will not use a selector; other will. In general, it is effective to keep the "best" organisms from one generation to the next, so that good genes do not become lost at random. This is, of course, an improvement on nature, where being "the best" doesnt guarantee survival.
Reproduction
In most cases, a reproducer generates new organisms using parents selected (by fitness) from an existing population. In some singular (and probably rare) cases, a reproducer might generate new, random organisms in order to keep diversity high. Reproduction techniques can include crossover and asexual, sexual and (my favorite) try-sexual models.
Mutation Operators
A mutator applies mutations (random, usually small changes) to a set of organisms. Mutation is highly dependent on the type of organism. In traditional genetic algorithms, a mutation flips one or more bits in an integer (i.e., chromosome). Evolving a path for the Traveling Salesman Problem involves complex mutations that maintain valid permutations of destination points; in the case of floating-point numbers, Ive provided utilities for mutating and crossing IEC-60559 (IEEE- 754) float and double types.
Enhancements:
- Minor bugfixes, code cleanups, and changes to pseudo-random number generators.
- Now includes Visual Studio 2005 projects along with GNU build files.

VETH is a daemon that creates a virtual ethernet card in Linux. This is done via the Universal TUN/ TAP Driver. It is useful to request more than one IP address via DHCP with a virtual ethernet card attached to an existing NIC.

Linux has an implementation that does the work, but partially. Sometimes, this emulation doesnt work as expected. Because of this, I wrote VETH, to be helpful in this situations.

For example, if you want to have more than one IP address obtained via DHCP probably you know thats impossible. With VETH you can attach a virtual ethernet into an existent NIC card, and the run dhclient in it to obtain a new IP.

Perhaps you are saying "hey, man, dont mess with me, I can do that with aliasing. With an ifconfig eth0:1 I have a new ethernet". OK, perhaps, perhaps...

It isnt 100% true. Look at this scenario:

You have a DSL modem working as a bridge. You have a firewall with exactly 2 NICs, no more. One of these NICs is crossover-connected to your modem, and another is in your internal subnet.

Santa Fe Desktop Linux is an easy to use desktop operating system. It puts some of the worlds best open source applications within the reach of non-technical users. It even runs right off the CD so you can try it without installing.
Santa Fe Desktop Linux was built following these design goals:
Make it familiar. Present the user a familiar interface where they dont have to guess which buttons do what.
Keep it small. The distribution should install and run from a single CD.
Make it useful to normal users. The distribution should be useful to a large non-technical audience.
Keep it fun. Make sure audio and video work to the best of their abilities so the users can play games and enjoy multimedia without hassle.
Leave the user alone. Hardware should always be automatically detected and configured without the users help. Software configuration should automatically have sane defaults.
Unlike other operating systems, Santa Fe is designed to automatically configure itself everytime it runs. It will auto-detect the right drivers for your hardware and configure it all to the best of its abilities. No more troublesome driver installs. Santa Fe works best in Plug and Play and DHCP environments.
Main features:
- A viable alternative to your current operating system (OS).
- Imagine if your OS came preinstalled with a fully featured photo editing and image creation program.
- Imagine if every OS included an animation and 3D graphics creation program.
- What if your OS came standard with finance management and desktop publishing applications?.
- Now imagine if all those things were available for $39.95.
- Santa Fe Linux offers the open source solution to the seemingly impossible dream described above. Santa Fe comes with a program called the GIMP, a fully featured digital photo editing and image/graphics creation program. Blender, another standard program, is a 3D graphics, animation, rendering, and post production program. Managing finances is easy with GNU Cash, an open source program that gets your finances organized quickly. Desktop publishing is simple with Scribus, a program that allows you to create everything from newsletters to a fully produced magazine.
- Also, Santa Fe features a full office suite that is compatible with Microsoft? Word, Excel, Powerpoint, and Outlook.
- Additional programs that come with Santa Fe Linux:
- Gnome Meeting: Video teleconferencing application.
- Audacity: Records, renders, and applies digital effects to audio.
- Kino: Digital video editor.
- XMMS: Audio player that supports a wide variety of audio file formats.
- Anjuta: Developers program which allows users to create their own applications/programs.
- Also, at a price of 82.99, Santa Fe is now available with Codeweavers Crossover Office. This program allows users to install the Microsoft? Office Suite including Word, Excel, Powerpoint, Outlook, and Access.

Fast Genetic Algorithm is a simple yet powerful implementation of a general genetic algorithm, and provides many types of crossover and selection procedures.
It is suitable to solve mathematical problems such as combinatorical optimization ones, as well as to build artificial life simulations.
Written in C++, the library is released under the terms of the GNU Lesser General Public License, and its easy to incorporate in other applications.
Further improvements include parallelization of the algorithm in multi-processor environments and general performance optimizations.
You can download the current development snapshot, which is a working but not fully tested version of the library.
Enhancements:
- Dynamic arrays were fixed to compile even on non-C99 compilers (like MSVC).
- A switch to choose whether to preserve the fittest individual across generations was added.
- The pthreads-win32 library was included in the package, as well as Visual C++ and Dev-C++ projects to easily build the source code on Windows.
- A function that computes the standard deviation of fitness values was added (thanks to Jonas Neubert for the contribution).

PyGEP project is a simple library suitable for academic study of GEP (Gene Expression Programming) in Python 2.5, aiming for ease of use and rapid implementation.
It provides standard multigenic chromosomes; a population class using elitism and fitness scaling for selection; mutation, crossover and transposition operators; and some standard GEP functions and linkers.
PyGEP is intended for research, not commercial application. Those interested in a full GEP system are advised to visit Gepsoft, makers of GeneXproTools.
Enhancements:
- This release incorporates extensive stability testing, code cleanup per cheesecake and pylint, and documentation updates.
- Also, as a minor performance enhancement, gene evaluation lists only expand attributes inside their coding regions.