Complexity and non-commutativity of learning operations on graphs
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 noncommutative. 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.
|Keywords||No keywords specified (fix it)|
No categories specified
(categorize this paper)
References found in this work BETA
No references found.
Citations of this work BETA
Non-Classical Correlations in Bistable Perception?Thomas Filk - 2011 - Axiomathes 21 (2):221-232.
Similar books and articles
Peirce, Logic Diagrams, and the Elementary Operations of Reasoning.P. N. Johnson-Laird - 2002 - Thinking and Reasoning 8 (1):69 – 95.
Learning-in-Practise: The Social Complexity of Learning in Working Life.Elena P. Antonacopoulou - unknown
Input/Output Logics.Makinson David & van der Torre Leendert - 2000 - Journal of Philosophical Logic 29 (4):383-408.
Old Ideas, New Mistakes: All Learning is Relational.Stellan Ohlsson - 1997 - Behavioral and Brain Sciences 20 (1):79-80.
Bilingual Second Language Learning Strategies in Eritrea with Reference to Reading, Writing and Vocabulary.Tecle Ghebremuse - manuscript
Spontaneous Coordination and Evolutionary Learning Processes in an Agent-Based Model.Pierre Barbaroux & Gilles Enée - 2005 - Mind and Society 4 (2):179-195.
Added to index2009-01-28
Total downloads16 ( #297,935 of 2,170,068 )
Recent downloads (6 months)2 ( #186,298 of 2,170,068 )
How can I increase my downloads?