spacecruft
/
karoo_gp
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Update index.html

gh-pages
Kai Staats 2017-02-09 22:34:32 -07:00 committed by GitHub
parent 46b4485e7c
commit 00f852df87
1 changed files with 5 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
index.html
View File

@ -19,7 +19,7 @@
</section>
<section class="main-content">
<p><a href="http://www.kaistaats.com/wp-content/uploads/2016/07/screenshot_karoo_gp_desktop.png"><img src="http://www.kaistaats.com/wp-content/uploads/2016/07/screenshot_karoo_gp_desktop-224x300.png" alt="Karoo GP by Kai Staats" width="224" height="300" hspace="20" align="left"></a> Karoo GP is a evolutionary algorithm, a genetic programming application suite written in Python which provides both symbolic regression and classification analysis. Karoo GP is a scalable platform with multicore support, designed to readily work with realworld data. <em>No programming required.</em> As a teaching tool, it enables instructors to share step-by-step how an evolutionary algorithm arrives to its solution. As a hands-on learning tool, Karoo GP supports rapid, repeatable experimentation.</p>
<p><a href="http://www.kaistaats.com/wp-content/uploads/2016/07/screenshot_karoo_gp_desktop.png"><img src="http://www.kaistaats.com/wp-content/uploads/2016/07/screenshot_karoo_gp_desktop-224x300.png" alt="Karoo GP by Kai Staats" width="224" height="300" hspace="20" align="left"></a> Karoo GP is a evolutionary algorithm, a genetic programming application suite written in Python which provides both symbolic regression and classification analysis. Karoo GP is a scalable platform with multicore and GPU support, designed to readily work with realworld data. <em>No programming required.</em> As a teaching tool, it enables instructors to share step-by-step how an evolutionary algorithm arrives to its solution. As a hands-on learning tool, Karoo GP supports rapid, repeatable experimentation.</p>
<p>Karoo GP includes a Desktop application with an intuitive user interface, a fully scriptable Server application with user defined default parameters and command-line arguments; a stand-alone Python script which generates randomly constructed subsets of larger datasets and another which normalises datasets; and a toy model which shows the inner workings of multiclass classification.</p>
@ -31,15 +31,12 @@
<ul>
<li>written in Object Oriented Python with a hierarchical naming scheme for all methods</li>
<li>multi-core support (extensive testing on 24-40 CPUs)</li>
<li>
<em>Desktop</em> application provides a simple user interface with menu, 5 display modes (see below), and runtime reconfiguration of parameters</li>
<li>
<em>Server</em> script provides a configuration file for readily repeated GP runs and command-line arguments</li>
<li>multicore and GPU support through the TensorFlow library</li>
<li><em>Desktop</em> script provides a simple user interface with menu, 5 display modes (see below), and runtime reconfiguration of parameters</li>
<li><em>Server</em> script enables configurable runs via command-line arguments</li>
<li>anticipates datasets as standard .csv files</li>
<li>records the full population of each generation to a .csv file</li>
<li>automatically archives the population of each generation and runtime parameters</li>
<li>supports customised seed populations</li>
<li>supports arithmetic (+, -, *, /, **, sqrt), trigonometric (cos, sin), and boolean (and, or) operators</li>
<li>relatively simple framework for preparing custom fitness functions and evaluation routines</li>
</ul>
@ -55,6 +52,5 @@
</section>
</body>
</html>