ART Models in SNNS

This section will describe the use of the three ART models ART1, ART2 and ARTMAP, as they are implemented in SNNS. It will not give detailed information on the   Adaptive Resonance Theory. You should already know the theory to be able to understand this chapter. For the theory the following literature is recommended:

[CG87a]
Original paper, describing ART1 theory.
[CG87b]
Original paper, describing ART2 theory.
[CG91]
Original paper, describing ARTMAP theory.
[Her92]
Description of theory, implementation and application of the ART models in SNNS (in German).

There will be one subsection for each of the three models and one subsection describing the required topologies of the networks when using the ART learning-, update- or initialization-functions. These topologies are rather complex. For this reason the network creation tool BigNet has been extended. It now offers an easy way to create ART1, ART2 and ARTMAP networks according to your requirements. For a detailed explanation of the respective features of BigNet see chapter .

• ART1
  • Structure of an ART1 Network
  • Using ART1 Networks in SNNS
    • ART1 Initialization Function
    • ART1 Learning Function
    • ART1 Update Functions
• ART2
  • Structure of an ART2 Network
  • Using ART2 Networks in SNNS
    • ART2 Initialization Function
    • ART2 Learning Function
    • ART2 Update Functions
• ARTMAP
  • Structure of an ARTMAP Network
  • Using ARTMAP Networks in SNNS
    • ARTMAP Initialization Function
    • ARTMAP Learning Function
    • ARTMAP Update Functions
• Topology of ART Networks in SNNS