Neural Java
Neural Networks Tutorial
with Java Applets
|
Introduction
Neural Java is a series of exercises and demos. Each exercise consists
of a short introduction, a small demonstration program written in Java
(Java Applet), and a series of questions which are intended as an invitation
to play with the programs and explore the possibilities of different algorithms.
The aim of the applets is to illustrate the dynamics of different artificial
neural networks. Emphasis has been put on visualization and interactive
interfaces.
The Java Applets are not intended for and not useful for
large-scale applications! Users interested in application programs should use
other simulators.
The list below covers standard neural network algorithms
like BackProp, Kohonen, and the Hopfield model.
It also includes some models that
are more biological,
and features visualizations of the Hodgkin-Huxley and the integrate-and-fire
models.
Additional material
The following are available for download:
See also
Exercises
If there is this image
on the right of the link, then you can download the applet in order to execute it at your place. And if there is this image
on the right of the link, then you can download the source code of the applet. But you must agree before with the GNU General Public Licence.
If so follow the instructions here to download and install the applets.
Single Neurons
- Artificial Neuron.
 
- McCulloch-Pitts Neuron.
 
- Spiking Neuron.
(Requires Swing).
 
- Hodgkin-Huxley Model.
 
- Axons and Action Potential Propagation.
 
Supervised Learning
Single-layer networks (simple perceptrons)
-
Perceptron Learning Rule.
 
- Adaline, Perceptron and Backpropagation.
 
Multi-layer networks
-
Multi-layer Perceptron (with neuron outputs in {0;1}).
 
- Multi-layer Perceptron (with neuron outputs in {-1;1}).
 
- Multi-layer Perceptron and C language.

- Generalization in Multi-layer Perceptrons (with neuron outputs in {0;1}).
 
- Generalization in Multi-layer Perceptrons (with neuron outputs in {-1;1}).
 
- Optical Character Recognition with Multi-layer Perceptron.
 
- Prediction with Multi-layer Perceptron.
 
Density Estimation and Interpolation
- Radial Basis Function Network.
 
- Gaussian Mixture Model / EM.
 
Unsupervised Learning
- Principal Component Analysis.
 
- PCA for Character Recognition.
- Competitive Learning Methods.
 
Reinforcement Learning
- Blackjack and Reinforcement Learning.
 
Network Dynamics
- Hopfield Network.
 
- Pseudoinverse Network.
 
- Network of spiking neurons.
(Requires Swing).
 
- Retina Simulation. (Runs very slow with some netscape versions).
 
URL: http://diwww.epfl.ch/mantra/tutorial/english/
Last updated: 06-October-2000 by Sébastien Baehni