Nonlinear Sciences – Adaptation and Self-Organizing Systems
Scientific paper
2005-12-20
BioSystems 85, 84-93 (2006)
Nonlinear Sciences
Adaptation and Self-Organizing Systems
18 pages, 6 figures, 5 tables, submitted for publication in BioSystems
Scientific paper
We present results from numerical studies of supervised learning operations in recurrent networks considered as graphs, leading from a given set of input conditions to predetermined outputs. Graphs that have optimized their output for particular inputs with respect to predetermined outputs are asymptotically stable and can be characterized by attractors which form a representation space for an associative multiplicative structure of input operations. As the mapping from a series of inputs onto a series of such attractors generally depends on the sequence of inputs, this structure is generally non-commutative. Moreover, the size of the set of attractors, indicating the complexity of learning, is found to behave non-monotonically as learning proceeds. A tentative relation between this complexity and the notion of pragmatic information is indicated.
Atmanspacher Harald
Filk Thomas
No associations
LandOfFree
Complexity and Non-Commutativity of Learning Operations on Graphs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Complexity and Non-Commutativity of Learning Operations on Graphs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Complexity and Non-Commutativity of Learning Operations on Graphs will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-662373