neural network entertainment

" There are three kinds of death in this world. There's heart death, there's brain death, and there's being off the network."
- Guy Almes

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! If you are interested in application programs, you should use other simulators.

The list below covers standard neural network algorithms like BackPropagation, Kohonen, and the Hopfield model.

Additional material

See the resources section for additional material.   You can also refer to:
Spiking Neurons (745K Postscript) (W. Gerstner, from Pulsed Neural Networks, Maass and Bishop eds., MIT Press 1998).
Supervised Learning for Neural Networks: a tutorial with JAVA exercises (850K Postscript) (W. Gerstner).
For more sample programs, also refer to Neural Networks at Your Fingertips.
Check what other people have said in the Forum.


Single Neurons
  1. Artificial Neuron.
  2. Axons and Action Potential Propagation.
Supervised Learning
Single-layer networks (simple perceptrons)
    1. Perceptron Learning Rule.
    2. Adaline, Perceptron and Backpropagation.

    Multi-layer networks
    1. Multi-layer Perceptron (with neuron outputs in {0;1}).
    2. Multi-layer Perceptron (with neuron outputs in {-1;1}).
    3. Multi-layer Perceptron and C language.
    4. Generalization in Multi-layer Perceptrons (with neuron outputs in {0;1}).
    5. Generalization in Multi-layer Perceptrons (with neuron outputs in {-1;1})
    6. Optical Character Recognition with Multi-layer Perceptron.
    7. Prediction with Multi-layer Perceptron.
Density Estimation and Interpolation
  1. Radial Basis Function Network.
  2. Gaussian Mixture Model / EM.
Unsupervised Learning
  1. Principal Component Analysis.
  2. Competitive Learning Methods.
Reinforcement Learning
  1. Blackjack and Reinforcement Learning.
Network Dynamics
  1. Hopfield Network.
  2. Pseudoinverse Network.
  3. Network of spiking neurons. (Requires Swing)
  4. Retina Simulation. (Runs very slow with some versions of Netscape)


Credits: Links obtained from