Experimental Visualization of Artificial Neural Network with WebGL
by Markus Sprunck
This experiment shows an Artificial Neural Network which learns to detect the frequency of
the input signal independent from the phase. The implementation is based on Three.js (r56), Guava and
Google Web Toolkit. GWT helps to translate the Java code for the Artificial Neural Network
into JavaScript, which is then executed in the browser. The experiment has been developed with
GWT 2.6.0 and App Engine SDK 1.9.30. You may read more and
get the source code
here.