This is the experimental version of ra25, used for experimenting with parameters and different algorithm variants etc.
The standard ra25 should be used as a template for new projects, and does not contain this experimental stuff.. It only has minimal parameters relative to defaults.
ra25x runs a simple random-associator four-layer axon network
that uses the standard supervised learning paradigm to learn
mappings between 25 random input / output patterns
defined over 5x5 input / output layers (i.e., 25 units)
README
¶
Documentation
Source Files