Algorithms

 

The algorithms are meant for more sophisticated computing. This group includes the following algorithms:

• TS-SOM
• some versions of the backpropagation training
• some of the typical statistical clustering algorithms
• multidimensional projections: Sammon's mapping, classical scaling

• The Tree-Structured Self-Organizing Map and related structures
  • Training a TS-SOM
  • Classifying data by a TS-SOM
  • Smoothing data in a TS-SOM
  • Creating a field for TS-SOM layer information
  • Storing the indexes of neurons into a data frame
  • Getting and setting data in a TS-SOM layer
  • Computing a U-matrix
  • Spreading the groups of core neurons
  • Mapping data records onto a TS-SOM
  • Generating data according to the grid of a TS-SOM
• Backpropagation
  • The basic learning rule
  • The basic learning rule with a momentum term
  • Global adaptive training step length
  • The Matlab neural network toolbox style training
  • The Silva & Almeida training
  • The RPROP training
  • The Levenberg-Marquard training
  • Importing a new data to a trained network
  • Visualizing an MLP network
• Classical scaling and Sammon's mapping
• Data clustering
  • Hierarchical clustering
  • k-means clustering
  • Fuzzy c-means clustering