• New homepages

  Now also available general information on Self-Organizing Map (SOM) through these pages. You may enter these pages through this link.

• New Demo Version of Nenet v1.1 is now available

New features and bug fixes:

• Quantization and topographic errors are now calculated and shown with the map.
• Active neuron coordinates are now displayed.
• Preprocessing logic fully fixed: Preprocessing can now only be performed in the map initialization phase. The obtained preprocessing parameters will then be used in all successive phases.
• Preprocessing parameters are saved to the file making it possible to continue processing the map with the initially chosen preprocessing method.
• Initialization & training history for the map is now saved in the map header.
• Changes to the visualization types: Labels are now shown with a smaller font.
• Histogram 3D visualization grid is now displayed correctly. Also the bottom plate has been removed.
• Labelling is now easier:
  • A label can be added by just double clicking a neuron.
  • All labels can be removed from a single neuron or from the entire map.
• Several bug fixes:
  • A serious bug fix in the preprocessing fixed -> prevented large data from being processed. (more than 46340 vectors caused problems)
  • Memory allocation problems for labels fixed.
  • Map and data loading can now handle large data.
  • Map and data loading is now more error tolerant.
• Cosmetic changes including new flat toolbar outlook.
• Snap shot of the map can now be copied to clipboard in bitmap format and can be therefore embedded to other applications.

• Initial version 1.0 of Nenet released

  Currently implemented features:

  • Implements the standard Kohonen SOM algorithm.
  • Supports 2 common data preprocessing methods.
  • 5 different visualization methods with rectangular and hexagonal topology.
    • Standard 2D
    • Interpolate 2D
    • Histogram 2D
    • Histogram 3D
    • Parameter Level
  • Capability to animate both train and test sequences in all visualization methods.
  • Labelling:
    • Both neurons and parameter levels can be labelled.
    • Provides also autolabelling.
  • Neuron values can be inspected easily.
  • Arbitrary selection of parameter levels can be visualized with Umatrix simultaneously.
  • Multiple views can be opened on the same map data.
  • Maps can be printed
  • Extensive help system provides fast and accurate online help.
  • SOM_PAK compatible file formats.
  • Easy to Install and uninstall
  • Uses Windows 95 & Windows NT multitasking capabilities.
  • 32-bit Windows 95/NT application making Nenet easy to use in an ordinary PC.
  • Conforms to the common Windows application style - all functionality in one application.

   

Copyright (c) 1996-1999 By the Nenet Team