logo_lcn
EPFL
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. Moreover 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

  1. Artificial Neuron. Artificial neuron classes Artificial neuron sources
  2. McCulloch-Pitts Neuron. McCulloch-Pitts classes  McCulloch-Pitts sources
  3. Spiking Neuron. (Requires Swing). Spiking neuron classes  Spiking neuron sources
  4. Hodgkin-Huxley Model. Hodgkin-Huxley classes  Hodgkin-Huxley sources
  5. Axons and Action Potential Propagation. Axon classes  Axon sources

Supervised Learning

    1. Perceptron Learning Rule. Perceptron classes  Perceptron sources
    2. Adaline, Perceptron and Backpropagation. Adaline, perceptron and backprop classes  Adaline, perceptron and backprop sources
    Multi-layer networks
    1. Multi-layer Perceptron (with neuron outputs in {0;1}). Multi-layer Perceptron classes  Multi-layer Perceptron sources
    2. Multi-layer Perceptron (with neuron outputs in {-1;1}). Multi-layer Perceptron (-1,1) classes  Multi-layer Perceptron (-1,1) sources
    3. Multi-layer Perceptron and C language. Multi-layer Perceptron (in C) source file
    4. Generalization in Multi-layer Perceptrons (with neuron outputs in {0;1}). Generalization classes  Generalization sources
    5. Generalization in Multi-layer Perceptrons (with neuron outputs in {-1;1}). Generalization (-1,1) classes  Generalization (-1,1) sources
    6. Optical Character Recognition with Multi-layer Perceptron. OCR classes  OCR sources
    7. Prediction with Multi-layer Perceptron. Prediction classes  Prediction sources
Support Vector Machine
  1. Support Vector Machine with a polynomial kernel.

Density Estimation and Interpolation

  1. Radial Basis Function Network. RBF classes  RBF sources
  2. Gaussian Mixture Model / EM. Gaussian MM classes  Gaussian MM sources
  3. Mixture model, using unlabeled data Code source

Unsupervised Learning

  1. Principal Component Analysis. PCA classes  PCA sources
  2. PCA for Character Recognition.
  3. Competitive Learning Methods. Competitive Learning classes  Competitive Learning sources

Reinforcement Learning

  1. Blackjack and Reinforcement Learning. Blackjack classes  Blackjack sources

Network Dynamics

  1. Hopfield Network. Hopfield classes  Hopfield sources
  2. Pseudoinverse Network. Pseudoinverse classes  Pseudoinverse sources
  3. Network of spiking neurons. (Requires Swing). Spiking neuron classes  Spiking neuron sources
  4. Retina Simulation. (Runs very slow with some netscape versions). Retina classes  Retina sources

Miniproject

Miniproject for Postgraduate Training

Useful links


URL: http://lcn.epfl.ch/tutorial/english/
Last updated: 06-October-2000 by Sébastien Baehni