Java MLP Backprop Code 

Get a quick start to coding your first neural network with this code for a multilayer percepron trained with the backpropagation learning algorithm. Submitted:

Java Neural Network Software Available 

This is to announce the availability of a Java implementation of the following algorithms and neural network models: * Hard Competitive Learning (standard algorithm) * Neural Gas (Martinetz and Schulten 1991) ... The software can be accessed at http://www.neuroinformatik.ruhrunibochum.de/ini/VDM/research/gsn/DemoGNG/GNG.html where it is embedded as Java applet into a Web page and is downloaded for immediate execution when you visit this page (if you have a slow link or only ftp access, please see below). Submitted: Dec 01, 1999

MultiLayer Perceptron 

This is a multilayer perceptron applet. Submitted: Nov 07, 1999

Neural Net Components in an Object Oriented Class Structure 

Neural Net Components in an Object Oriented Class Structure: The classes are all written in Java (JDK Version 1.0.2) and contain components of the Backpropagation Net and the Kohonen Feature Map neural network types. Submitted: Nov 21, 1999

Perceptron Learning 

This applet demonstrates a simple form of supervised learning entitled the perceptron learning algorithm. Using this applet, you can train the perceptron to act as a binary logic unit. It can compute or approximate most 2input Boolean functions. Submitted: Nov 07, 1999

SOM: SelfOrganizing Maps 

Java applet, implements several methods related to competitive learning. It is possible to experiment with the methods using various data distributions and observe the learning process. A common terminology is used to make it easy to compare one method to the other. Submitted: Nov 07, 1999

Neural Nets for Control 

Consider the problem of balancing a ball on an adjustable beam as shown in Figure 4. The ball starts with an initial position and initial velocity, and we require the ball to be brought to a rest at the center of the beam by dynamically adjusting the angle of the beam. This problem is a classic regulatortype control problem and is precisely posed as: Given any initial condition, what is an appropriate control signal, which can produce the desired final state? A neural net can be trained to learn such a control by observing the actions of a skilled human operator... The given applet demonstrates the Ball Balancing Problem. Submitted: Nov 07, 1999

Learning of Function Approximation 

The following applet can be used to experiment with backprop learning for function approximation problems. Submitted: Nov 07, 1999

Perceptron Learning Rule (CNNL) 

This program applies the perceptron learning rule to generate a separating surface for a two class problem (classes X and O). The X's are represented by a Red Box while the O's are represented by a Purple Box. Submitted: Nov 07, 1999

Principal Component Extraction via Various HebbianType Rules (CNNL) 

This applet implements three different learning rules for extracting the major principal component for an arbitrary zeromean distribution. These rules are Normalized Hebbian rule, Oja's rule, and Yullie et al rule as discribed by Equations (3.3.5), (3.3.6), and (3.3.7) on page 92 in Mohamad Hassoun's textbook. Submitted: Nov 07, 1999

Temporal Difference Learning Project 

Java sources for TD learning applets of Tic Tac Toe and random walk. Submitted:

Clustering via Simple Competitive Learning (CNNL) 

This is a program that impliments the simple competitive learning process as described on page 103 in M. Hassoun, Fundementals of Artificial Neural Networks. Submitted: Nov 07, 1999

2 Dimensional Linear Dynamical Systems (CNNL) 

This page contains a java program that starts an applet which plots 2D Time Dynamical functions. Submitted: Nov 07, 1999

